diff --git "a/sf_log.txt" "b/sf_log.txt" --- "a/sf_log.txt" +++ "b/sf_log.txt" @@ -1,100 +1,44 @@ -[2023-03-02 18:27:42,253][1037367] Saving configuration to /home/qgallouedec/train_dir/default_experiment/config.json... -[2023-03-02 18:27:42,253][1037367] Rollout worker 0 uses device cpu -[2023-03-02 18:27:42,253][1037367] Rollout worker 1 uses device cpu -[2023-03-02 18:27:42,253][1037367] Rollout worker 2 uses device cpu -[2023-03-02 18:27:42,253][1037367] Rollout worker 3 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 4 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 5 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 6 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 7 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 8 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 9 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 10 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 11 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 12 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 13 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 14 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 15 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 16 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 17 uses device cpu -[2023-03-02 18:27:42,254][1037367] Rollout worker 18 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 19 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 20 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 21 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 22 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 23 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 24 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 25 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 26 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 27 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 28 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 29 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 30 uses device cpu -[2023-03-02 18:27:42,255][1037367] Rollout worker 31 uses device cpu -[2023-03-02 18:27:42,270][1037367] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:27:42,270][1037367] InferenceWorker_p0-w0: min num requests: 10 -[2023-03-02 18:27:42,335][1037367] Starting all processes... -[2023-03-02 18:27:42,335][1037367] Starting process learner_proc0 -[2023-03-02 18:27:42,385][1037367] Starting all processes... -[2023-03-02 18:27:42,434][1037367] Starting process inference_proc0-0 -[2023-03-02 18:27:42,434][1037367] Starting process rollout_proc0 -[2023-03-02 18:27:42,434][1037367] Starting process rollout_proc1 -[2023-03-02 18:27:42,434][1037367] Starting process rollout_proc2 -[2023-03-02 18:27:42,435][1037367] Starting process rollout_proc3 -[2023-03-02 18:27:42,435][1037367] Starting process rollout_proc4 -[2023-03-02 18:27:42,437][1037367] Starting process rollout_proc5 -[2023-03-02 18:27:42,438][1037367] Starting process rollout_proc6 -[2023-03-02 18:27:42,438][1037367] Starting process rollout_proc7 -[2023-03-02 18:27:42,438][1037367] Starting process rollout_proc8 -[2023-03-02 18:27:42,449][1037367] Starting process rollout_proc9 -[2023-03-02 18:27:42,451][1037367] Starting process rollout_proc10 -[2023-03-02 18:27:42,452][1037367] Starting process rollout_proc11 -[2023-03-02 18:27:42,452][1037367] Starting process rollout_proc12 -[2023-03-02 18:27:42,452][1037367] Starting process rollout_proc13 -[2023-03-02 18:27:42,457][1037367] Starting process rollout_proc14 -[2023-03-02 18:27:42,459][1037367] Starting process rollout_proc15 -[2023-03-02 18:27:42,460][1037367] Starting process rollout_proc16 -[2023-03-02 18:27:42,561][1037367] Starting process rollout_proc31 -[2023-03-02 18:27:42,464][1037367] Starting process rollout_proc18 -[2023-03-02 18:27:42,470][1037367] Starting process rollout_proc19 -[2023-03-02 18:27:42,475][1037367] Starting process rollout_proc20 -[2023-03-02 18:27:42,483][1037367] Starting process rollout_proc21 -[2023-03-02 18:27:42,486][1037367] Starting process rollout_proc22 -[2023-03-02 18:27:42,502][1037367] Starting process rollout_proc24 -[2023-03-02 18:27:42,509][1037367] Starting process rollout_proc25 -[2023-03-02 18:27:42,496][1037367] Starting process rollout_proc23 -[2023-03-02 18:27:42,517][1037367] Starting process rollout_proc26 -[2023-03-02 18:27:42,526][1037367] Starting process rollout_proc27 -[2023-03-02 18:27:42,544][1037367] Starting process rollout_proc29 -[2023-03-02 18:27:42,535][1037367] Starting process rollout_proc28 -[2023-03-02 18:27:42,552][1037367] Starting process rollout_proc30 -[2023-03-02 18:27:42,463][1037367] Starting process rollout_proc17 -[2023-03-02 18:27:44,359][1037628] Worker 3 uses CPU cores [3] -[2023-03-02 18:27:44,419][1037626] Worker 1 uses CPU cores [1] -[2023-03-02 18:27:44,515][1037794] Worker 14 uses CPU cores [14] -[2023-03-02 18:27:44,674][1037630] Worker 5 uses CPU cores [5] -[2023-03-02 18:27:44,678][1037934] Worker 28 uses CPU cores [28] -[2023-03-02 18:27:44,854][1037790] Worker 10 uses CPU cores [10] -[2023-03-02 18:27:44,990][1037830] Worker 21 uses CPU cores [21] -[2023-03-02 18:27:45,050][1037901] Worker 29 uses CPU cores [29] -[2023-03-02 18:27:45,278][1037793] Worker 13 uses CPU cores [13] -[2023-03-02 18:27:45,342][1037798] Worker 18 uses CPU cores [18] -[2023-03-02 18:27:45,506][1037896] Worker 22 uses CPU cores [22] -[2023-03-02 18:27:45,654][1037863] Worker 31 uses CPU cores [31] -[2023-03-02 18:27:45,666][1037795] Worker 15 uses CPU cores [15] -[2023-03-02 18:27:45,822][1037573] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:27:45,822][1037573] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-03-02 18:27:45,833][1037573] Num visible devices: 1 -[2023-03-02 18:27:45,867][1037573] WARNING! It is generally recommended to enable Fixed KL loss (https://arxiv.org/pdf/1707.06347.pdf) for continuous action tasks to avoid potential numerical issues. I.e. set --kl_loss_coeff=0.1 -[2023-03-02 18:27:45,867][1037573] Starting seed is not provided -[2023-03-02 18:27:45,867][1037573] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:27:45,868][1037573] Initializing actor-critic model on device cuda:0 -[2023-03-02 18:27:45,868][1037573] RunningMeanStd input shape: (39,) -[2023-03-02 18:27:45,868][1037573] RunningMeanStd input shape: (1,) -[2023-03-02 18:27:45,870][1037935] Worker 17 uses CPU cores [17] -[2023-03-02 18:27:45,911][1037625] Worker 0 uses CPU cores [0] -[2023-03-02 18:27:45,999][1037573] Created Actor Critic model with architecture: -[2023-03-02 18:27:45,999][1037573] ActorCriticSharedWeights( +[2023-03-03 11:18:30,885][16922] Saving configuration to /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/config.json... +[2023-03-03 11:18:30,909][16922] Rollout worker 0 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 1 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 2 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 3 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 4 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 5 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 6 uses device cpu +[2023-03-03 11:18:30,910][16922] Rollout worker 7 uses device cpu +[2023-03-03 11:19:39,471][16994] Saving configuration to /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/config.json... +[2023-03-03 11:19:39,496][16994] Rollout worker 0 uses device cpu +[2023-03-03 11:19:39,496][16994] Rollout worker 1 uses device cpu +[2023-03-03 11:19:39,496][16994] Rollout worker 2 uses device cpu +[2023-03-03 11:19:39,497][16994] Rollout worker 3 uses device cpu +[2023-03-03 11:19:39,497][16994] Rollout worker 4 uses device cpu +[2023-03-03 11:19:39,497][16994] Rollout worker 5 uses device cpu +[2023-03-03 11:19:39,497][16994] Rollout worker 6 uses device cpu +[2023-03-03 11:19:39,497][16994] Rollout worker 7 uses device cpu +[2023-03-03 11:19:39,675][16994] InferenceWorker_p0-w0: min num requests: 2 +[2023-03-03 11:19:39,713][16994] Starting all processes... +[2023-03-03 11:19:39,714][16994] Starting process learner_proc0 +[2023-03-03 11:19:39,772][16994] Starting all processes... +[2023-03-03 11:19:39,793][16994] Starting process inference_proc0-0 +[2023-03-03 11:19:39,799][16994] Starting process rollout_proc0 +[2023-03-03 11:19:39,800][16994] Starting process rollout_proc1 +[2023-03-03 11:19:39,804][16994] Starting process rollout_proc2 +[2023-03-03 11:19:39,813][16994] Starting process rollout_proc3 +[2023-03-03 11:19:39,817][16994] Starting process rollout_proc4 +[2023-03-03 11:19:39,826][16994] Starting process rollout_proc5 +[2023-03-03 11:19:39,827][16994] Starting process rollout_proc6 +[2023-03-03 11:19:39,828][16994] Starting process rollout_proc7 +[2023-03-03 11:19:43,526][17030] WARNING! It is generally recommended to enable Fixed KL loss (https://arxiv.org/pdf/1707.06347.pdf) for continuous action tasks to avoid potential numerical issues. I.e. set --kl_loss_coeff=0.1 +[2023-03-03 11:19:43,526][17030] Starting seed is not provided +[2023-03-03 11:19:43,526][17030] Initializing actor-critic model on device cpu +[2023-03-03 11:19:43,526][17030] RunningMeanStd input shape: (39,) +[2023-03-03 11:19:43,528][17030] RunningMeanStd input shape: (1,) +[2023-03-03 11:19:43,570][17037] On MacOS, not setting affinity +[2023-03-03 11:19:43,571][17039] On MacOS, not setting affinity +[2023-03-03 11:19:43,666][17034] On MacOS, not setting affinity +[2023-03-03 11:19:43,669][17030] Created Actor Critic model with architecture: +[2023-03-03 11:19:43,669][17030] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( @@ -127,2633 +71,780 @@ (distribution_linear): Linear(in_features=512, out_features=8, bias=True) ) ) -[2023-03-02 18:27:46,049][1037713] Worker 8 uses CPU cores [8] -[2023-03-02 18:27:46,106][1037792] Worker 12 uses CPU cores [12] -[2023-03-02 18:27:46,230][1037797] Worker 19 uses CPU cores [19] -[2023-03-02 18:27:46,467][1037631] Worker 6 uses CPU cores [6] -[2023-03-02 18:27:46,486][1037791] Worker 11 uses CPU cores [11] -[2023-03-02 18:27:46,583][1037899] Worker 26 uses CPU cores [26] -[2023-03-02 18:27:46,851][1037624] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:27:46,851][1037624] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-03-02 18:27:46,875][1037624] Num visible devices: 1 -[2023-03-02 18:27:46,965][1037862] Worker 20 uses CPU cores [20] -[2023-03-02 18:27:46,968][1037900] Worker 27 uses CPU cores [27] -[2023-03-02 18:27:47,098][1037796] Worker 16 uses CPU cores [16] -[2023-03-02 18:27:47,176][1037864] Worker 24 uses CPU cores [24] -[2023-03-02 18:27:47,250][1037897] Worker 25 uses CPU cores [25] -[2023-03-02 18:27:47,288][1037898] Worker 23 uses CPU cores [23] -[2023-03-02 18:27:47,467][1037573] Using optimizer -[2023-03-02 18:27:47,467][1037573] No checkpoints found -[2023-03-02 18:27:47,467][1037573] Did not load from checkpoint, starting from scratch! -[2023-03-02 18:27:47,467][1037573] Initialized policy 0 weights for model version 0 -[2023-03-02 18:27:47,469][1037573] LearnerWorker_p0 finished initialization! -[2023-03-02 18:27:47,469][1037573] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:27:47,490][1037933] Worker 30 uses CPU cores [30] -[2023-03-02 18:27:47,505][1037694] Worker 9 uses CPU cores [9] -[2023-03-02 18:27:47,526][1037624] RunningMeanStd input shape: (39,) -[2023-03-02 18:27:47,527][1037624] RunningMeanStd input shape: (1,) -[2023-03-02 18:27:47,639][1037627] Worker 2 uses CPU cores [2] -[2023-03-02 18:27:47,693][1037629] Worker 4 uses CPU cores [4] -[2023-03-02 18:27:47,747][1037758] Worker 7 uses CPU cores [7] -[2023-03-02 18:27:48,148][1037367] Inference worker 0-0 is ready! -[2023-03-02 18:27:48,149][1037367] All inference workers are ready! Signal rollout workers to start! -[2023-03-02 18:27:49,284][1037367] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:27:49,695][1037933] EvtLoop [rollout_proc30_evt_loop, process=rollout_proc30] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,697][1037933] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc30_evt_loop -[2023-03-02 18:27:49,748][1037758] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,750][1037758] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc7_evt_loop -[2023-03-02 18:27:49,750][1037934] EvtLoop [rollout_proc28_evt_loop, process=rollout_proc28] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,752][1037934] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc28_evt_loop -[2023-03-02 18:27:49,759][1037901] EvtLoop [rollout_proc29_evt_loop, process=rollout_proc29] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,761][1037901] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc29_evt_loop -[2023-03-02 18:27:49,770][1037625] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,772][1037625] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc0_evt_loop -[2023-03-02 18:27:49,787][1037797] EvtLoop [rollout_proc19_evt_loop, process=rollout_proc19] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,789][1037797] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc19_evt_loop -[2023-03-02 18:27:49,813][1037627] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,815][1037627] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc2_evt_loop -[2023-03-02 18:27:49,815][1037899] EvtLoop [rollout_proc26_evt_loop, process=rollout_proc26] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,817][1037899] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc26_evt_loop -[2023-03-02 18:27:49,817][1037629] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,817][1037900] EvtLoop [rollout_proc27_evt_loop, process=rollout_proc27] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,817][1037862] EvtLoop [rollout_proc20_evt_loop, process=rollout_proc20] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,818][1037629] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc4_evt_loop -[2023-03-02 18:27:49,818][1037900] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc27_evt_loop -[2023-03-02 18:27:49,818][1037862] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc20_evt_loop -[2023-03-02 18:27:49,840][1037796] EvtLoop [rollout_proc16_evt_loop, process=rollout_proc16] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,841][1037796] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc16_evt_loop -[2023-03-02 18:27:49,843][1037897] EvtLoop [rollout_proc25_evt_loop, process=rollout_proc25] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,845][1037897] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc25_evt_loop -[2023-03-02 18:27:49,845][1037626] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,846][1037626] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc1_evt_loop -[2023-03-02 18:27:49,847][1037935] EvtLoop [rollout_proc17_evt_loop, process=rollout_proc17] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,849][1037935] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc17_evt_loop -[2023-03-02 18:27:49,850][1037863] EvtLoop [rollout_proc31_evt_loop, process=rollout_proc31] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,850][1037795] EvtLoop [rollout_proc15_evt_loop, process=rollout_proc15] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,852][1037863] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc31_evt_loop -[2023-03-02 18:27:49,852][1037795] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc15_evt_loop -[2023-03-02 18:27:49,859][1037798] EvtLoop [rollout_proc18_evt_loop, process=rollout_proc18] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,860][1037798] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc18_evt_loop -[2023-03-02 18:27:49,860][1037791] EvtLoop [rollout_proc11_evt_loop, process=rollout_proc11] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,862][1037791] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc11_evt_loop -[2023-03-02 18:27:49,934][1037631] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,936][1037631] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc6_evt_loop -[2023-03-02 18:27:49,944][1037630] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,948][1037630] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc5_evt_loop -[2023-03-02 18:27:49,950][1037694] EvtLoop [rollout_proc9_evt_loop, process=rollout_proc9] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,952][1037694] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc9_evt_loop -[2023-03-02 18:27:49,963][1037830] EvtLoop [rollout_proc21_evt_loop, process=rollout_proc21] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,964][1037830] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc21_evt_loop -[2023-03-02 18:27:49,968][1037864] EvtLoop [rollout_proc24_evt_loop, process=rollout_proc24] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,970][1037864] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc24_evt_loop -[2023-03-02 18:27:49,977][1037713] EvtLoop [rollout_proc8_evt_loop, process=rollout_proc8] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,981][1037713] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc8_evt_loop -[2023-03-02 18:27:49,981][1037896] EvtLoop [rollout_proc22_evt_loop, process=rollout_proc22] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:49,983][1037896] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc22_evt_loop -[2023-03-02 18:27:50,031][1037628] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,032][1037628] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc3_evt_loop -[2023-03-02 18:27:50,058][1037790] EvtLoop [rollout_proc10_evt_loop, process=rollout_proc10] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,059][1037790] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc10_evt_loop -[2023-03-02 18:27:50,069][1037898] EvtLoop [rollout_proc23_evt_loop, process=rollout_proc23] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,070][1037898] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc23_evt_loop -[2023-03-02 18:27:50,070][1037792] EvtLoop [rollout_proc12_evt_loop, process=rollout_proc12] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,072][1037792] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc12_evt_loop -[2023-03-02 18:27:50,115][1037793] EvtLoop [rollout_proc13_evt_loop, process=rollout_proc13] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,117][1037793] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc13_evt_loop -[2023-03-02 18:27:50,513][1037794] EvtLoop [rollout_proc14_evt_loop, process=rollout_proc14] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() -Traceback (most recent call last): - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal - slot_callable(*args) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init - env_runner.init(self.timing) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init - self._reset() - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset - observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/core.py", line 323, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset - obs, info = self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/time_limit.py", line 68, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/order_enforcing.py", line 42, in reset - return self.env.reset(**kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/wrappers/env_checker.py", line 45, in reset - return env_reset_passive_checker(self.env, **kwargs) - File "/home/qgallouedec/env_sample_factory/lib/python3.9/site-packages/gym/utils/passive_env_checker.py", line 192, in env_reset_passive_checker - result = env.reset(**kwargs) -TypeError: reset() got an unexpected keyword argument 'seed' -[2023-03-02 18:27:50,519][1037794] Unhandled exception reset() got an unexpected keyword argument 'seed' in evt loop rollout_proc14_evt_loop -[2023-03-02 18:27:54,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:27:59,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:02,265][1037367] Heartbeat connected on Batcher_0 -[2023-03-02 18:28:02,267][1037367] Heartbeat connected on LearnerWorker_p0 -[2023-03-02 18:28:02,313][1037367] Heartbeat connected on InferenceWorker_p0-w0 -[2023-03-02 18:28:04,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:09,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:14,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:19,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:24,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:29,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:34,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:39,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:44,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:49,284][1037367] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:28:53,935][1037367] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1037367], exiting... -[2023-03-02 18:28:53,936][1037367] Runner profile tree view: -main_loop: 71.6008 -[2023-03-02 18:28:53,936][1037367] Collected {0: 0}, FPS: 0.0 -[2023-03-02 18:28:53,936][1037573] Stopping Batcher_0... -[2023-03-02 18:28:53,936][1037573] Loop batcher_evt_loop terminating... -[2023-03-02 18:28:53,937][1037573] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth... -[2023-03-02 18:28:53,972][1037573] Stopping LearnerWorker_p0... -[2023-03-02 18:28:53,972][1037573] Loop learner_proc0_evt_loop terminating... -[2023-03-02 18:28:53,990][1037624] Weights refcount: 2 0 -[2023-03-02 18:28:53,991][1037624] Stopping InferenceWorker_p0-w0... -[2023-03-02 18:28:53,991][1037624] Loop inference_proc0-0_evt_loop terminating... -[2023-03-02 18:29:12,579][1041156] Saving configuration to /home/qgallouedec/train_dir/default_experiment/config.json... -[2023-03-02 18:29:12,580][1041156] Rollout worker 0 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 1 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 2 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 3 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 4 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 5 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 6 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 7 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 8 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 9 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 10 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 11 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 12 uses device cpu -[2023-03-02 18:29:12,580][1041156] Rollout worker 13 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 14 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 15 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 16 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 17 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 18 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 19 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 20 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 21 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 22 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 23 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 24 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 25 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 26 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 27 uses device cpu -[2023-03-02 18:29:12,581][1041156] Rollout worker 28 uses device cpu -[2023-03-02 18:29:12,582][1041156] Rollout worker 29 uses device cpu -[2023-03-02 18:29:12,582][1041156] Rollout worker 30 uses device cpu -[2023-03-02 18:29:12,582][1041156] Rollout worker 31 uses device cpu -[2023-03-02 18:29:12,596][1041156] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:29:12,596][1041156] InferenceWorker_p0-w0: min num requests: 10 -[2023-03-02 18:29:12,662][1041156] Starting all processes... -[2023-03-02 18:29:12,662][1041156] Starting process learner_proc0 -[2023-03-02 18:29:12,712][1041156] Starting all processes... -[2023-03-02 18:29:12,721][1041156] Starting process inference_proc0-0 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc0 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc1 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc2 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc3 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc4 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc5 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc6 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc7 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc8 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc9 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc10 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc11 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc12 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc13 -[2023-03-02 18:29:12,722][1041156] Starting process rollout_proc14 -[2023-03-02 18:29:12,737][1041156] Starting process rollout_proc16 -[2023-03-02 18:29:12,730][1041156] Starting process rollout_proc15 -[2023-03-02 18:29:12,744][1041156] Starting process rollout_proc17 -[2023-03-02 18:29:12,761][1041156] Starting process rollout_proc18 -[2023-03-02 18:29:12,781][1041156] Starting process rollout_proc19 -[2023-03-02 18:29:12,784][1041156] Starting process rollout_proc20 -[2023-03-02 18:29:12,789][1041156] Starting process rollout_proc21 -[2023-03-02 18:29:12,797][1041156] Starting process rollout_proc22 -[2023-03-02 18:29:12,803][1041156] Starting process rollout_proc23 -[2023-03-02 18:29:12,825][1041156] Starting process rollout_proc24 -[2023-03-02 18:29:12,840][1041156] Starting process rollout_proc25 -[2023-03-02 18:29:12,851][1041156] Starting process rollout_proc26 -[2023-03-02 18:29:12,858][1041156] Starting process rollout_proc27 -[2023-03-02 18:29:12,859][1041156] Starting process rollout_proc28 -[2023-03-02 18:29:12,860][1041156] Starting process rollout_proc29 -[2023-03-02 18:29:12,862][1041156] Starting process rollout_proc30 -[2023-03-02 18:29:12,957][1041156] Starting process rollout_proc31 -[2023-03-02 18:29:14,702][1041406] Worker 5 uses CPU cores [5] -[2023-03-02 18:29:14,825][1041399] Worker 0 uses CPU cores [0] -[2023-03-02 18:29:14,869][1041633] Worker 18 uses CPU cores [18] -[2023-03-02 18:29:15,038][1041568] Worker 13 uses CPU cores [13] -[2023-03-02 18:29:15,126][1041768] Worker 29 uses CPU cores [29] -[2023-03-02 18:29:15,162][1041634] Worker 19 uses CPU cores [19] -[2023-03-02 18:29:15,386][1041400] Worker 1 uses CPU cores [1] -[2023-03-02 18:29:15,463][1041803] Worker 25 uses CPU cores [25] -[2023-03-02 18:29:15,554][1041403] Worker 6 uses CPU cores [6] -[2023-03-02 18:29:15,612][1041735] Worker 28 uses CPU cores [28] -[2023-03-02 18:29:15,641][1041771] Worker 24 uses CPU cores [24] -[2023-03-02 18:29:15,915][1041699] Worker 22 uses CPU cores [22] -[2023-03-02 18:29:15,972][1041470] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:29:15,972][1041470] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-03-02 18:29:15,982][1041470] Num visible devices: 1 -[2023-03-02 18:29:16,066][1041769] Worker 30 uses CPU cores [30] -[2023-03-02 18:29:16,283][1041507] Worker 4 uses CPU cores [4] -[2023-03-02 18:29:16,338][1041601] Worker 15 uses CPU cores [15] -[2023-03-02 18:29:16,476][1041701] Worker 23 uses CPU cores [23] -[2023-03-02 18:29:16,546][1041698] Worker 14 uses CPU cores [14] -[2023-03-02 18:29:16,641][1041402] Worker 3 uses CPU cores [3] -[2023-03-02 18:29:16,735][1041703] Worker 27 uses CPU cores [27] -[2023-03-02 18:29:16,922][1041566] Worker 11 uses CPU cores [11] -[2023-03-02 18:29:17,072][1041348] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:29:17,072][1041348] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-03-02 18:29:17,082][1041348] Num visible devices: 1 -[2023-03-02 18:29:17,088][1041404] Worker 8 uses CPU cores [8] -[2023-03-02 18:29:17,111][1041348] WARNING! It is generally recommended to enable Fixed KL loss (https://arxiv.org/pdf/1707.06347.pdf) for continuous action tasks to avoid potential numerical issues. I.e. set --kl_loss_coeff=0.1 -[2023-03-02 18:29:17,111][1041348] Starting seed is not provided -[2023-03-02 18:29:17,111][1041348] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:29:17,111][1041348] Initializing actor-critic model on device cuda:0 -[2023-03-02 18:29:17,112][1041348] RunningMeanStd input shape: (39,) -[2023-03-02 18:29:17,112][1041348] RunningMeanStd input shape: (1,) -[2023-03-02 18:29:17,206][1041348] Created Actor Critic model with architecture: -[2023-03-02 18:29:17,206][1041348] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): MlpEncoder( - (mlp_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ELU) - (2): RecursiveScriptModule(original_name=Linear) - (3): RecursiveScriptModule(original_name=ELU) - ) - ) - ) - ) - (core): ModelCoreRNN( - (core): GRU(512, 512) - ) - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=8, bias=True) - ) -) -[2023-03-02 18:29:17,280][1041539] Worker 12 uses CPU cores [12] -[2023-03-02 18:29:17,350][1041405] Worker 7 uses CPU cores [7] -[2023-03-02 18:29:17,527][1041702] Worker 20 uses CPU cores [20] -[2023-03-02 18:29:17,556][1041767] Worker 26 uses CPU cores [26] -[2023-03-02 18:29:17,626][1041600] Worker 16 uses CPU cores [16] -[2023-03-02 18:29:17,738][1041567] Worker 9 uses CPU cores [9] -[2023-03-02 18:29:17,891][1041697] Worker 17 uses CPU cores [17] -[2023-03-02 18:29:18,018][1041401] Worker 2 uses CPU cores [2] -[2023-03-02 18:29:18,126][1041770] Worker 31 uses CPU cores [31] -[2023-03-02 18:29:18,297][1041407] Worker 10 uses CPU cores [10] -[2023-03-02 18:29:18,337][1041700] Worker 21 uses CPU cores [21] -[2023-03-02 18:29:18,445][1041348] Using optimizer -[2023-03-02 18:29:18,446][1041348] Loading state from checkpoint /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth... -[2023-03-02 18:29:18,450][1041348] Loading model from checkpoint -[2023-03-02 18:29:18,451][1041348] Loaded experiment state at self.train_step=0, self.env_steps=0 -[2023-03-02 18:29:18,451][1041348] Initialized policy 0 weights for model version 0 -[2023-03-02 18:29:18,453][1041348] LearnerWorker_p0 finished initialization! -[2023-03-02 18:29:18,453][1041348] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:29:18,524][1041470] RunningMeanStd input shape: (39,) -[2023-03-02 18:29:18,525][1041470] RunningMeanStd input shape: (1,) -[2023-03-02 18:29:19,153][1041156] Inference worker 0-0 is ready! -[2023-03-02 18:29:19,153][1041156] All inference workers are ready! Signal rollout workers to start! -[2023-03-02 18:29:19,652][1041156] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:29:20,736][1041698] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,754][1041770] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,772][1041701] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,797][1041404] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,802][1041697] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,805][1041699] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,839][1041768] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,856][1041735] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,859][1041702] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,868][1041767] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,876][1041400] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,877][1041771] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,885][1041700] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,886][1041406] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,889][1041566] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,889][1041703] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,892][1041803] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,908][1041399] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,909][1041401] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,911][1041633] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,931][1041634] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,944][1041407] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,947][1041568] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,964][1041402] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,973][1041405] Decorrelating experience for 0 frames... -[2023-03-02 18:29:20,998][1041567] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,001][1041769] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,007][1041507] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,011][1041539] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,106][1041600] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,115][1041403] Decorrelating experience for 0 frames... -[2023-03-02 18:29:21,226][1041601] Decorrelating experience for 0 frames... -[2023-03-02 18:29:22,292][1041770] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,309][1041698] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,349][1041701] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,396][1041768] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,405][1041404] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,405][1041735] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,413][1041697] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,436][1041399] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,448][1041400] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,472][1041634] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,478][1041767] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,496][1041700] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,499][1041803] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,503][1041406] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,517][1041566] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,517][1041407] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,517][1041703] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,543][1041568] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,545][1041567] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,547][1041771] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,551][1041401] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,552][1041633] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,568][1041539] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,574][1041405] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,581][1041699] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,584][1041702] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,584][1041507] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,660][1041769] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,688][1041403] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,717][1041402] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,768][1041600] Decorrelating experience for 32 frames... -[2023-03-02 18:29:22,835][1041601] Decorrelating experience for 32 frames... -[2023-03-02 18:29:23,020][1041348] Signal inference workers to stop experience collection... -[2023-03-02 18:29:23,023][1041470] InferenceWorker_p0-w0: stopping experience collection -[2023-03-02 18:29:23,374][1041348] Signal inference workers to resume experience collection... -[2023-03-02 18:29:23,374][1041470] InferenceWorker_p0-w0: resuming experience collection -[2023-03-02 18:29:24,581][1041470] Updated weights for policy 0, policy_version 10 (0.0212) -[2023-03-02 18:29:24,652][1041156] Fps is (10 sec: 2252.9, 60 sec: 2252.9, 300 sec: 2252.9). Total num frames: 11264. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-03-02 18:29:25,407][1041470] Updated weights for policy 0, policy_version 20 (0.0007) -[2023-03-02 18:29:26,248][1041470] Updated weights for policy 0, policy_version 30 (0.0007) -[2023-03-02 18:29:27,088][1041470] Updated weights for policy 0, policy_version 40 (0.0007) -[2023-03-02 18:29:27,920][1041470] Updated weights for policy 0, policy_version 50 (0.0007) -[2023-03-02 18:29:28,750][1041470] Updated weights for policy 0, policy_version 60 (0.0007) -[2023-03-02 18:29:29,585][1041470] Updated weights for policy 0, policy_version 70 (0.0006) -[2023-03-02 18:29:29,652][1041156] Fps is (10 sec: 7168.1, 60 sec: 7168.1, 300 sec: 7168.1). Total num frames: 71680. Throughput: 0: 5557.1. Samples: 55570. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:29:29,652][1041156] Avg episode reward: [(0, '6.776')] -[2023-03-02 18:29:30,399][1041470] Updated weights for policy 0, policy_version 80 (0.0006) -[2023-03-02 18:29:31,229][1041470] Updated weights for policy 0, policy_version 90 (0.0006) -[2023-03-02 18:29:32,072][1041470] Updated weights for policy 0, policy_version 100 (0.0006) -[2023-03-02 18:29:32,591][1041156] Heartbeat connected on Batcher_0 -[2023-03-02 18:29:32,594][1041156] Heartbeat connected on LearnerWorker_p0 -[2023-03-02 18:29:32,599][1041156] Heartbeat connected on RolloutWorker_w0 -[2023-03-02 18:29:32,600][1041156] Heartbeat connected on InferenceWorker_p0-w0 -[2023-03-02 18:29:32,601][1041156] Heartbeat connected on RolloutWorker_w1 -[2023-03-02 18:29:32,604][1041156] Heartbeat connected on RolloutWorker_w2 -[2023-03-02 18:29:32,605][1041156] Heartbeat connected on RolloutWorker_w3 -[2023-03-02 18:29:32,608][1041156] Heartbeat connected on RolloutWorker_w4 -[2023-03-02 18:29:32,611][1041156] Heartbeat connected on RolloutWorker_w6 -[2023-03-02 18:29:32,614][1041156] Heartbeat connected on RolloutWorker_w7 -[2023-03-02 18:29:32,616][1041156] Heartbeat connected on RolloutWorker_w8 -[2023-03-02 18:29:32,619][1041156] Heartbeat connected on RolloutWorker_w10 -[2023-03-02 18:29:32,620][1041156] Heartbeat connected on RolloutWorker_w9 -[2023-03-02 18:29:32,620][1041156] Heartbeat connected on RolloutWorker_w5 -[2023-03-02 18:29:32,622][1041156] Heartbeat connected on RolloutWorker_w11 -[2023-03-02 18:29:32,623][1041156] Heartbeat connected on RolloutWorker_w12 -[2023-03-02 18:29:32,626][1041156] Heartbeat connected on RolloutWorker_w13 -[2023-03-02 18:29:32,628][1041156] Heartbeat connected on RolloutWorker_w14 -[2023-03-02 18:29:32,629][1041156] Heartbeat connected on RolloutWorker_w15 -[2023-03-02 18:29:32,631][1041156] Heartbeat connected on RolloutWorker_w16 -[2023-03-02 18:29:32,634][1041156] Heartbeat connected on RolloutWorker_w17 -[2023-03-02 18:29:32,635][1041156] Heartbeat connected on RolloutWorker_w18 -[2023-03-02 18:29:32,637][1041156] Heartbeat connected on RolloutWorker_w19 -[2023-03-02 18:29:32,639][1041156] Heartbeat connected on RolloutWorker_w20 -[2023-03-02 18:29:32,641][1041156] Heartbeat connected on RolloutWorker_w21 -[2023-03-02 18:29:32,645][1041156] Heartbeat connected on RolloutWorker_w22 -[2023-03-02 18:29:32,645][1041156] Heartbeat connected on RolloutWorker_w23 -[2023-03-02 18:29:32,649][1041156] Heartbeat connected on RolloutWorker_w24 -[2023-03-02 18:29:32,649][1041156] Heartbeat connected on RolloutWorker_w25 -[2023-03-02 18:29:32,651][1041156] Heartbeat connected on RolloutWorker_w26 -[2023-03-02 18:29:32,654][1041156] Heartbeat connected on RolloutWorker_w27 -[2023-03-02 18:29:32,655][1041156] Heartbeat connected on RolloutWorker_w28 -[2023-03-02 18:29:32,658][1041156] Heartbeat connected on RolloutWorker_w29 -[2023-03-02 18:29:32,660][1041156] Heartbeat connected on RolloutWorker_w30 -[2023-03-02 18:29:32,663][1041156] Heartbeat connected on RolloutWorker_w31 -[2023-03-02 18:29:32,889][1041470] Updated weights for policy 0, policy_version 110 (0.0006) -[2023-03-02 18:29:33,723][1041470] Updated weights for policy 0, policy_version 120 (0.0007) -[2023-03-02 18:29:34,567][1041470] Updated weights for policy 0, policy_version 130 (0.0006) -[2023-03-02 18:29:34,652][1041156] Fps is (10 sec: 12185.5, 60 sec: 8874.8, 300 sec: 8874.8). Total num frames: 133120. Throughput: 0: 8620.8. Samples: 129310. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:34,652][1041156] Avg episode reward: [(0, '11.346')] -[2023-03-02 18:29:34,659][1041348] Saving new best policy, reward=11.346! -[2023-03-02 18:29:35,365][1041470] Updated weights for policy 0, policy_version 140 (0.0006) -[2023-03-02 18:29:36,204][1041470] Updated weights for policy 0, policy_version 150 (0.0006) -[2023-03-02 18:29:37,057][1041470] Updated weights for policy 0, policy_version 160 (0.0006) -[2023-03-02 18:29:37,884][1041470] Updated weights for policy 0, policy_version 170 (0.0006) -[2023-03-02 18:29:38,687][1041470] Updated weights for policy 0, policy_version 180 (0.0006) -[2023-03-02 18:29:39,521][1041470] Updated weights for policy 0, policy_version 190 (0.0006) -[2023-03-02 18:29:39,652][1041156] Fps is (10 sec: 12390.4, 60 sec: 9779.3, 300 sec: 9779.3). Total num frames: 195584. Throughput: 0: 8317.0. Samples: 166339. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:39,652][1041156] Avg episode reward: [(0, '16.348')] -[2023-03-02 18:29:39,655][1041348] Saving new best policy, reward=16.348! -[2023-03-02 18:29:40,340][1041470] Updated weights for policy 0, policy_version 200 (0.0006) -[2023-03-02 18:29:41,144][1041470] Updated weights for policy 0, policy_version 210 (0.0007) -[2023-03-02 18:29:41,968][1041470] Updated weights for policy 0, policy_version 220 (0.0006) -[2023-03-02 18:29:42,777][1041470] Updated weights for policy 0, policy_version 230 (0.0006) -[2023-03-02 18:29:43,619][1041470] Updated weights for policy 0, policy_version 240 (0.0008) -[2023-03-02 18:29:44,440][1041470] Updated weights for policy 0, policy_version 250 (0.0007) -[2023-03-02 18:29:44,652][1041156] Fps is (10 sec: 12492.9, 60 sec: 10322.0, 300 sec: 10322.0). Total num frames: 258048. Throughput: 0: 9655.9. Samples: 241394. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:44,652][1041156] Avg episode reward: [(0, '18.740')] -[2023-03-02 18:29:44,652][1041348] Saving new best policy, reward=18.740! -[2023-03-02 18:29:45,246][1041470] Updated weights for policy 0, policy_version 260 (0.0007) -[2023-03-02 18:29:46,072][1041470] Updated weights for policy 0, policy_version 270 (0.0006) -[2023-03-02 18:29:46,915][1041470] Updated weights for policy 0, policy_version 280 (0.0007) -[2023-03-02 18:29:47,729][1041470] Updated weights for policy 0, policy_version 290 (0.0007) -[2023-03-02 18:29:48,542][1041470] Updated weights for policy 0, policy_version 300 (0.0007) -[2023-03-02 18:29:49,366][1041470] Updated weights for policy 0, policy_version 310 (0.0006) -[2023-03-02 18:29:49,652][1041156] Fps is (10 sec: 12492.9, 60 sec: 10683.8, 300 sec: 10683.8). Total num frames: 320512. Throughput: 0: 10536.5. Samples: 316092. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:49,652][1041156] Avg episode reward: [(0, '19.417')] -[2023-03-02 18:29:49,655][1041348] Saving new best policy, reward=19.417! -[2023-03-02 18:29:50,178][1041470] Updated weights for policy 0, policy_version 320 (0.0007) -[2023-03-02 18:29:51,011][1041470] Updated weights for policy 0, policy_version 330 (0.0007) -[2023-03-02 18:29:51,839][1041470] Updated weights for policy 0, policy_version 340 (0.0006) -[2023-03-02 18:29:52,654][1041470] Updated weights for policy 0, policy_version 350 (0.0007) -[2023-03-02 18:29:53,478][1041470] Updated weights for policy 0, policy_version 360 (0.0006) -[2023-03-02 18:29:54,287][1041470] Updated weights for policy 0, policy_version 370 (0.0007) -[2023-03-02 18:29:54,652][1041156] Fps is (10 sec: 12492.7, 60 sec: 10942.2, 300 sec: 10942.2). Total num frames: 382976. Throughput: 0: 10100.3. Samples: 353507. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:54,652][1041156] Avg episode reward: [(0, '18.078')] -[2023-03-02 18:29:55,119][1041470] Updated weights for policy 0, policy_version 380 (0.0007) -[2023-03-02 18:29:55,918][1041470] Updated weights for policy 0, policy_version 390 (0.0006) -[2023-03-02 18:29:56,746][1041470] Updated weights for policy 0, policy_version 400 (0.0006) -[2023-03-02 18:29:57,563][1041470] Updated weights for policy 0, policy_version 410 (0.0006) -[2023-03-02 18:29:58,388][1041470] Updated weights for policy 0, policy_version 420 (0.0007) -[2023-03-02 18:29:59,208][1041470] Updated weights for policy 0, policy_version 430 (0.0007) -[2023-03-02 18:29:59,652][1041156] Fps is (10 sec: 12492.7, 60 sec: 11136.1, 300 sec: 11136.1). Total num frames: 445440. Throughput: 0: 10714.5. Samples: 428578. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:29:59,652][1041156] Avg episode reward: [(0, '22.284')] -[2023-03-02 18:29:59,655][1041348] Saving new best policy, reward=22.284! -[2023-03-02 18:30:00,044][1041470] Updated weights for policy 0, policy_version 440 (0.0007) -[2023-03-02 18:30:00,863][1041470] Updated weights for policy 0, policy_version 450 (0.0006) -[2023-03-02 18:30:01,702][1041470] Updated weights for policy 0, policy_version 460 (0.0006) -[2023-03-02 18:30:02,551][1041470] Updated weights for policy 0, policy_version 470 (0.0007) -[2023-03-02 18:30:03,377][1041470] Updated weights for policy 0, policy_version 480 (0.0006) -[2023-03-02 18:30:04,199][1041470] Updated weights for policy 0, policy_version 490 (0.0006) -[2023-03-02 18:30:04,652][1041156] Fps is (10 sec: 12390.4, 60 sec: 11264.1, 300 sec: 11264.1). Total num frames: 506880. Throughput: 0: 11169.5. Samples: 502623. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:04,652][1041156] Avg episode reward: [(0, '27.631')] -[2023-03-02 18:30:04,652][1041348] Saving new best policy, reward=27.631! -[2023-03-02 18:30:05,041][1041470] Updated weights for policy 0, policy_version 500 (0.0006) -[2023-03-02 18:30:05,889][1041470] Updated weights for policy 0, policy_version 510 (0.0006) -[2023-03-02 18:30:06,704][1041470] Updated weights for policy 0, policy_version 520 (0.0007) -[2023-03-02 18:30:07,530][1041470] Updated weights for policy 0, policy_version 530 (0.0006) -[2023-03-02 18:30:08,365][1041470] Updated weights for policy 0, policy_version 540 (0.0006) -[2023-03-02 18:30:09,185][1041470] Updated weights for policy 0, policy_version 550 (0.0007) -[2023-03-02 18:30:09,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 11366.4, 300 sec: 11366.4). Total num frames: 568320. Throughput: 0: 11991.2. Samples: 539602. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:30:09,652][1041156] Avg episode reward: [(0, '24.110')] -[2023-03-02 18:30:10,027][1041470] Updated weights for policy 0, policy_version 560 (0.0006) -[2023-03-02 18:30:10,846][1041470] Updated weights for policy 0, policy_version 570 (0.0007) -[2023-03-02 18:30:11,651][1041470] Updated weights for policy 0, policy_version 580 (0.0006) -[2023-03-02 18:30:12,473][1041470] Updated weights for policy 0, policy_version 590 (0.0007) -[2023-03-02 18:30:13,310][1041470] Updated weights for policy 0, policy_version 600 (0.0007) -[2023-03-02 18:30:14,132][1041470] Updated weights for policy 0, policy_version 610 (0.0007) -[2023-03-02 18:30:14,651][1041156] Fps is (10 sec: 12390.5, 60 sec: 11468.9, 300 sec: 11468.9). Total num frames: 630784. Throughput: 0: 12406.1. Samples: 613845. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:30:14,652][1041156] Avg episode reward: [(0, '24.942')] -[2023-03-02 18:30:14,952][1041470] Updated weights for policy 0, policy_version 620 (0.0007) -[2023-03-02 18:30:15,790][1041470] Updated weights for policy 0, policy_version 630 (0.0006) -[2023-03-02 18:30:16,623][1041470] Updated weights for policy 0, policy_version 640 (0.0007) -[2023-03-02 18:30:17,458][1041470] Updated weights for policy 0, policy_version 650 (0.0006) -[2023-03-02 18:30:18,309][1041470] Updated weights for policy 0, policy_version 660 (0.0006) -[2023-03-02 18:30:19,150][1041470] Updated weights for policy 0, policy_version 670 (0.0007) -[2023-03-02 18:30:19,652][1041156] Fps is (10 sec: 12390.4, 60 sec: 11537.1, 300 sec: 11537.1). Total num frames: 692224. Throughput: 0: 12405.8. Samples: 687572. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:19,652][1041156] Avg episode reward: [(0, '37.811')] -[2023-03-02 18:30:19,665][1041348] Saving new best policy, reward=37.811! -[2023-03-02 18:30:19,982][1041470] Updated weights for policy 0, policy_version 680 (0.0006) -[2023-03-02 18:30:20,839][1041470] Updated weights for policy 0, policy_version 690 (0.0006) -[2023-03-02 18:30:21,655][1041470] Updated weights for policy 0, policy_version 700 (0.0006) -[2023-03-02 18:30:22,476][1041470] Updated weights for policy 0, policy_version 710 (0.0007) -[2023-03-02 18:30:23,313][1041470] Updated weights for policy 0, policy_version 720 (0.0007) -[2023-03-02 18:30:24,144][1041470] Updated weights for policy 0, policy_version 730 (0.0006) -[2023-03-02 18:30:24,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12373.3, 300 sec: 11594.9). Total num frames: 753664. Throughput: 0: 12399.4. Samples: 724313. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:24,652][1041156] Avg episode reward: [(0, '28.162')] -[2023-03-02 18:30:24,981][1041470] Updated weights for policy 0, policy_version 740 (0.0006) -[2023-03-02 18:30:25,823][1041470] Updated weights for policy 0, policy_version 750 (0.0006) -[2023-03-02 18:30:26,656][1041470] Updated weights for policy 0, policy_version 760 (0.0006) -[2023-03-02 18:30:27,483][1041470] Updated weights for policy 0, policy_version 770 (0.0007) -[2023-03-02 18:30:28,316][1041470] Updated weights for policy 0, policy_version 780 (0.0006) -[2023-03-02 18:30:29,160][1041470] Updated weights for policy 0, policy_version 790 (0.0006) -[2023-03-02 18:30:29,651][1041156] Fps is (10 sec: 12288.1, 60 sec: 12390.4, 300 sec: 11644.4). Total num frames: 815104. Throughput: 0: 12371.6. Samples: 798116. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:29,652][1041156] Avg episode reward: [(0, '23.295')] -[2023-03-02 18:30:29,981][1041470] Updated weights for policy 0, policy_version 800 (0.0007) -[2023-03-02 18:30:30,813][1041470] Updated weights for policy 0, policy_version 810 (0.0007) -[2023-03-02 18:30:31,625][1041470] Updated weights for policy 0, policy_version 820 (0.0006) -[2023-03-02 18:30:32,443][1041470] Updated weights for policy 0, policy_version 830 (0.0007) -[2023-03-02 18:30:33,254][1041470] Updated weights for policy 0, policy_version 840 (0.0006) -[2023-03-02 18:30:34,091][1041470] Updated weights for policy 0, policy_version 850 (0.0007) -[2023-03-02 18:30:34,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12390.4, 300 sec: 11687.3). Total num frames: 876544. Throughput: 0: 12364.9. Samples: 872511. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:34,652][1041156] Avg episode reward: [(0, '30.840')] -[2023-03-02 18:30:34,929][1041470] Updated weights for policy 0, policy_version 860 (0.0007) -[2023-03-02 18:30:35,799][1041470] Updated weights for policy 0, policy_version 870 (0.0007) -[2023-03-02 18:30:36,649][1041470] Updated weights for policy 0, policy_version 880 (0.0007) -[2023-03-02 18:30:37,472][1041470] Updated weights for policy 0, policy_version 890 (0.0007) -[2023-03-02 18:30:38,305][1041470] Updated weights for policy 0, policy_version 900 (0.0007) -[2023-03-02 18:30:39,149][1041470] Updated weights for policy 0, policy_version 910 (0.0006) -[2023-03-02 18:30:39,652][1041156] Fps is (10 sec: 12185.4, 60 sec: 12356.3, 300 sec: 11712.0). Total num frames: 936960. Throughput: 0: 12335.0. Samples: 908583. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:30:39,652][1041156] Avg episode reward: [(0, '30.760')] -[2023-03-02 18:30:40,006][1041470] Updated weights for policy 0, policy_version 920 (0.0006) -[2023-03-02 18:30:40,832][1041470] Updated weights for policy 0, policy_version 930 (0.0007) -[2023-03-02 18:30:41,688][1041470] Updated weights for policy 0, policy_version 940 (0.0007) -[2023-03-02 18:30:42,501][1041470] Updated weights for policy 0, policy_version 950 (0.0006) -[2023-03-02 18:30:43,308][1041470] Updated weights for policy 0, policy_version 960 (0.0006) -[2023-03-02 18:30:44,155][1041470] Updated weights for policy 0, policy_version 970 (0.0006) -[2023-03-02 18:30:44,651][1041156] Fps is (10 sec: 12185.7, 60 sec: 12339.2, 300 sec: 11745.9). Total num frames: 998400. Throughput: 0: 12304.6. Samples: 982283. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:44,652][1041156] Avg episode reward: [(0, '31.192')] -[2023-03-02 18:30:44,989][1041470] Updated weights for policy 0, policy_version 980 (0.0006) -[2023-03-02 18:30:45,832][1041470] Updated weights for policy 0, policy_version 990 (0.0007) -[2023-03-02 18:30:46,653][1041470] Updated weights for policy 0, policy_version 1000 (0.0006) -[2023-03-02 18:30:47,506][1041470] Updated weights for policy 0, policy_version 1010 (0.0006) -[2023-03-02 18:30:48,330][1041470] Updated weights for policy 0, policy_version 1020 (0.0006) -[2023-03-02 18:30:49,144][1041470] Updated weights for policy 0, policy_version 1030 (0.0006) -[2023-03-02 18:30:49,651][1041156] Fps is (10 sec: 12390.5, 60 sec: 12339.2, 300 sec: 11787.4). Total num frames: 1060864. Throughput: 0: 12299.3. Samples: 1056092. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:30:49,652][1041156] Avg episode reward: [(0, '32.916')] -[2023-03-02 18:30:49,982][1041470] Updated weights for policy 0, policy_version 1040 (0.0007) -[2023-03-02 18:30:50,805][1041470] Updated weights for policy 0, policy_version 1050 (0.0007) -[2023-03-02 18:30:51,623][1041470] Updated weights for policy 0, policy_version 1060 (0.0007) -[2023-03-02 18:30:52,416][1041470] Updated weights for policy 0, policy_version 1070 (0.0006) -[2023-03-02 18:30:53,226][1041470] Updated weights for policy 0, policy_version 1080 (0.0007) -[2023-03-02 18:30:54,085][1041470] Updated weights for policy 0, policy_version 1090 (0.0006) -[2023-03-02 18:30:54,652][1041156] Fps is (10 sec: 12492.7, 60 sec: 12339.2, 300 sec: 11824.5). Total num frames: 1123328. Throughput: 0: 12313.9. Samples: 1093727. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:30:54,652][1041156] Avg episode reward: [(0, '26.459')] -[2023-03-02 18:30:54,915][1041470] Updated weights for policy 0, policy_version 1100 (0.0006) -[2023-03-02 18:30:55,754][1041470] Updated weights for policy 0, policy_version 1110 (0.0006) -[2023-03-02 18:30:56,594][1041470] Updated weights for policy 0, policy_version 1120 (0.0006) -[2023-03-02 18:30:57,420][1041470] Updated weights for policy 0, policy_version 1130 (0.0006) -[2023-03-02 18:30:58,248][1041470] Updated weights for policy 0, policy_version 1140 (0.0006) -[2023-03-02 18:30:59,071][1041470] Updated weights for policy 0, policy_version 1150 (0.0006) -[2023-03-02 18:30:59,652][1041156] Fps is (10 sec: 12287.8, 60 sec: 12305.1, 300 sec: 11837.5). Total num frames: 1183744. Throughput: 0: 12308.1. Samples: 1167709. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:30:59,652][1041156] Avg episode reward: [(0, '22.995')] -[2023-03-02 18:30:59,915][1041470] Updated weights for policy 0, policy_version 1160 (0.0007) -[2023-03-02 18:31:00,748][1041470] Updated weights for policy 0, policy_version 1170 (0.0007) -[2023-03-02 18:31:01,582][1041470] Updated weights for policy 0, policy_version 1180 (0.0007) -[2023-03-02 18:31:02,407][1041470] Updated weights for policy 0, policy_version 1190 (0.0006) -[2023-03-02 18:31:03,250][1041470] Updated weights for policy 0, policy_version 1200 (0.0006) -[2023-03-02 18:31:04,068][1041470] Updated weights for policy 0, policy_version 1210 (0.0007) -[2023-03-02 18:31:04,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12322.1, 300 sec: 11868.7). Total num frames: 1246208. Throughput: 0: 12304.7. Samples: 1241284. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:31:04,652][1041156] Avg episode reward: [(0, '33.392')] -[2023-03-02 18:31:04,915][1041470] Updated weights for policy 0, policy_version 1220 (0.0007) -[2023-03-02 18:31:05,723][1041470] Updated weights for policy 0, policy_version 1230 (0.0007) -[2023-03-02 18:31:06,555][1041470] Updated weights for policy 0, policy_version 1240 (0.0007) -[2023-03-02 18:31:07,368][1041470] Updated weights for policy 0, policy_version 1250 (0.0006) -[2023-03-02 18:31:08,187][1041470] Updated weights for policy 0, policy_version 1260 (0.0006) -[2023-03-02 18:31:09,017][1041470] Updated weights for policy 0, policy_version 1270 (0.0007) -[2023-03-02 18:31:09,651][1041156] Fps is (10 sec: 12390.5, 60 sec: 12322.2, 300 sec: 11887.7). Total num frames: 1307648. Throughput: 0: 12311.8. Samples: 1278344. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:31:09,652][1041156] Avg episode reward: [(0, '24.287')] -[2023-03-02 18:31:09,655][1041348] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000001277_1307648.pth... -[2023-03-02 18:31:09,849][1041470] Updated weights for policy 0, policy_version 1280 (0.0006) -[2023-03-02 18:31:10,685][1041470] Updated weights for policy 0, policy_version 1290 (0.0007) -[2023-03-02 18:31:11,545][1041470] Updated weights for policy 0, policy_version 1300 (0.0006) -[2023-03-02 18:31:12,373][1041470] Updated weights for policy 0, policy_version 1310 (0.0007) -[2023-03-02 18:31:13,204][1041470] Updated weights for policy 0, policy_version 1320 (0.0006) -[2023-03-02 18:31:14,045][1041470] Updated weights for policy 0, policy_version 1330 (0.0006) -[2023-03-02 18:31:14,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12305.1, 300 sec: 11905.1). Total num frames: 1369088. Throughput: 0: 12316.8. Samples: 1352372. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:31:14,652][1041156] Avg episode reward: [(0, '24.567')] -[2023-03-02 18:31:14,859][1041470] Updated weights for policy 0, policy_version 1340 (0.0007) -[2023-03-02 18:31:15,707][1041470] Updated weights for policy 0, policy_version 1350 (0.0007) -[2023-03-02 18:31:16,536][1041470] Updated weights for policy 0, policy_version 1360 (0.0006) -[2023-03-02 18:31:17,360][1041470] Updated weights for policy 0, policy_version 1370 (0.0006) -[2023-03-02 18:31:18,188][1041470] Updated weights for policy 0, policy_version 1380 (0.0006) -[2023-03-02 18:31:19,038][1041470] Updated weights for policy 0, policy_version 1390 (0.0006) -[2023-03-02 18:31:19,652][1041156] Fps is (10 sec: 12287.9, 60 sec: 12305.1, 300 sec: 11921.1). Total num frames: 1430528. Throughput: 0: 12305.1. Samples: 1426239. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:31:19,652][1041156] Avg episode reward: [(0, '25.044')] -[2023-03-02 18:31:19,866][1041470] Updated weights for policy 0, policy_version 1400 (0.0007) -[2023-03-02 18:31:20,697][1041470] Updated weights for policy 0, policy_version 1410 (0.0008) -[2023-03-02 18:31:21,521][1041470] Updated weights for policy 0, policy_version 1420 (0.0007) -[2023-03-02 18:31:22,390][1041470] Updated weights for policy 0, policy_version 1430 (0.0005) -[2023-03-02 18:31:23,203][1041470] Updated weights for policy 0, policy_version 1440 (0.0007) -[2023-03-02 18:31:24,057][1041470] Updated weights for policy 0, policy_version 1450 (0.0008) -[2023-03-02 18:31:24,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12305.1, 300 sec: 11935.8). Total num frames: 1491968. Throughput: 0: 12325.3. Samples: 1463221. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:31:24,652][1041156] Avg episode reward: [(0, '21.030')] -[2023-03-02 18:31:24,893][1041470] Updated weights for policy 0, policy_version 1460 (0.0009) -[2023-03-02 18:31:25,683][1041470] Updated weights for policy 0, policy_version 1470 (0.0006) -[2023-03-02 18:31:26,536][1041470] Updated weights for policy 0, policy_version 1480 (0.0007) -[2023-03-02 18:31:27,348][1041470] Updated weights for policy 0, policy_version 1490 (0.0006) -[2023-03-02 18:31:28,161][1041470] Updated weights for policy 0, policy_version 1500 (0.0006) -[2023-03-02 18:31:28,973][1041470] Updated weights for policy 0, policy_version 1510 (0.0007) -[2023-03-02 18:31:29,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12305.0, 300 sec: 11949.3). Total num frames: 1553408. Throughput: 0: 12330.8. Samples: 1537168. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:31:29,652][1041156] Avg episode reward: [(0, '22.561')] -[2023-03-02 18:31:29,837][1041470] Updated weights for policy 0, policy_version 1520 (0.0007) -[2023-03-02 18:31:30,669][1041470] Updated weights for policy 0, policy_version 1530 (0.0006) -[2023-03-02 18:31:31,512][1041470] Updated weights for policy 0, policy_version 1540 (0.0006) -[2023-03-02 18:31:32,334][1041470] Updated weights for policy 0, policy_version 1550 (0.0006) -[2023-03-02 18:31:33,192][1041470] Updated weights for policy 0, policy_version 1560 (0.0006) -[2023-03-02 18:31:34,016][1041470] Updated weights for policy 0, policy_version 1570 (0.0007) -[2023-03-02 18:31:34,652][1041156] Fps is (10 sec: 12288.0, 60 sec: 12305.1, 300 sec: 11961.9). Total num frames: 1614848. Throughput: 0: 12320.2. Samples: 1610504. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0) -[2023-03-02 18:31:34,652][1041156] Avg episode reward: [(0, '29.190')] -[2023-03-02 18:31:34,880][1041470] Updated weights for policy 0, policy_version 1580 (0.0006) -[2023-03-02 18:31:35,724][1041470] Updated weights for policy 0, policy_version 1590 (0.0006) -[2023-03-02 18:31:36,452][1041156] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1041156], exiting... -[2023-03-02 18:31:36,452][1041700] Stopping RolloutWorker_w21... -[2023-03-02 18:31:36,452][1041567] Stopping RolloutWorker_w9... -[2023-03-02 18:31:36,452][1041404] Stopping RolloutWorker_w8... -[2023-03-02 18:31:36,452][1041703] Stopping RolloutWorker_w27... -[2023-03-02 18:31:36,452][1041601] Stopping RolloutWorker_w15... -[2023-03-02 18:31:36,453][1041404] Loop rollout_proc8_evt_loop terminating... -[2023-03-02 18:31:36,452][1041702] Stopping RolloutWorker_w20... -[2023-03-02 18:31:36,452][1041568] Stopping RolloutWorker_w13... -[2023-03-02 18:31:36,452][1041401] Stopping RolloutWorker_w2... -[2023-03-02 18:31:36,452][1041402] Stopping RolloutWorker_w3... -[2023-03-02 18:31:36,452][1041405] Stopping RolloutWorker_w7... -[2023-03-02 18:31:36,452][1041700] Loop rollout_proc21_evt_loop terminating... -[2023-03-02 18:31:36,452][1041156] Runner profile tree view: -main_loop: 143.7902 -[2023-03-02 18:31:36,453][1041567] Loop rollout_proc9_evt_loop terminating... -[2023-03-02 18:31:36,452][1041803] Stopping RolloutWorker_w25... -[2023-03-02 18:31:36,453][1041703] Loop rollout_proc27_evt_loop terminating... -[2023-03-02 18:31:36,452][1041539] Stopping RolloutWorker_w12... -[2023-03-02 18:31:36,452][1041403] Stopping RolloutWorker_w6... -[2023-03-02 18:31:36,452][1041769] Stopping RolloutWorker_w30... -[2023-03-02 18:31:36,452][1041767] Stopping RolloutWorker_w26... -[2023-03-02 18:31:36,452][1041633] Stopping RolloutWorker_w18... -[2023-03-02 18:31:36,452][1041771] Stopping RolloutWorker_w24... -[2023-03-02 18:31:36,452][1041400] Stopping RolloutWorker_w1... -[2023-03-02 18:31:36,453][1041735] Stopping RolloutWorker_w28... -[2023-03-02 18:31:36,452][1041566] Stopping RolloutWorker_w11... -[2023-03-02 18:31:36,453][1041702] Loop rollout_proc20_evt_loop terminating... -[2023-03-02 18:31:36,453][1041405] Loop rollout_proc7_evt_loop terminating... -[2023-03-02 18:31:36,453][1041601] Loop rollout_proc15_evt_loop terminating... -[2023-03-02 18:31:36,453][1041568] Loop rollout_proc13_evt_loop terminating... -[2023-03-02 18:31:36,452][1041768] Stopping RolloutWorker_w29... -[2023-03-02 18:31:36,452][1041770] Stopping RolloutWorker_w31... -[2023-03-02 18:31:36,453][1041399] Stopping RolloutWorker_w0... -[2023-03-02 18:31:36,453][1041156] Collected {0: 1636352}, FPS: 11380.1 -[2023-03-02 18:31:36,452][1041701] Stopping RolloutWorker_w23... -[2023-03-02 18:31:36,453][1041402] Loop rollout_proc3_evt_loop terminating... -[2023-03-02 18:31:36,453][1041401] Loop rollout_proc2_evt_loop terminating... -[2023-03-02 18:31:36,453][1041407] Stopping RolloutWorker_w10... -[2023-03-02 18:31:36,453][1041403] Loop rollout_proc6_evt_loop terminating... -[2023-03-02 18:31:36,453][1041507] Stopping RolloutWorker_w4... -[2023-03-02 18:31:36,453][1041400] Loop rollout_proc1_evt_loop terminating... -[2023-03-02 18:31:36,453][1041735] Loop rollout_proc28_evt_loop terminating... -[2023-03-02 18:31:36,453][1041769] Loop rollout_proc30_evt_loop terminating... -[2023-03-02 18:31:36,453][1041633] Loop rollout_proc18_evt_loop terminating... -[2023-03-02 18:31:36,453][1041699] Stopping RolloutWorker_w22... -[2023-03-02 18:31:36,453][1041539] Loop rollout_proc12_evt_loop terminating... -[2023-03-02 18:31:36,453][1041768] Loop rollout_proc29_evt_loop terminating... -[2023-03-02 18:31:36,453][1041803] Loop rollout_proc25_evt_loop terminating... -[2023-03-02 18:31:36,453][1041399] Loop rollout_proc0_evt_loop terminating... -[2023-03-02 18:31:36,453][1041771] Loop rollout_proc24_evt_loop terminating... -[2023-03-02 18:31:36,453][1041770] Loop rollout_proc31_evt_loop terminating... -[2023-03-02 18:31:36,453][1041566] Loop rollout_proc11_evt_loop terminating... -[2023-03-02 18:31:36,453][1041701] Loop rollout_proc23_evt_loop terminating... -[2023-03-02 18:31:36,453][1041407] Loop rollout_proc10_evt_loop terminating... -[2023-03-02 18:31:36,453][1041507] Loop rollout_proc4_evt_loop terminating... -[2023-03-02 18:31:36,453][1041767] Loop rollout_proc26_evt_loop terminating... -[2023-03-02 18:31:36,453][1041699] Loop rollout_proc22_evt_loop terminating... -[2023-03-02 18:31:36,453][1041634] Stopping RolloutWorker_w19... -[2023-03-02 18:31:36,454][1041634] Loop rollout_proc19_evt_loop terminating... -[2023-03-02 18:31:36,456][1041600] Stopping RolloutWorker_w16... -[2023-03-02 18:31:36,457][1041600] Loop rollout_proc16_evt_loop terminating... -[2023-03-02 18:31:36,457][1041348] Stopping Batcher_0... -[2023-03-02 18:31:36,458][1041348] Loop batcher_evt_loop terminating... -[2023-03-02 18:31:36,459][1041697] Stopping RolloutWorker_w17... -[2023-03-02 18:31:36,460][1041697] Loop rollout_proc17_evt_loop terminating... -[2023-03-02 18:31:36,462][1041698] Stopping RolloutWorker_w14... -[2023-03-02 18:31:36,463][1041698] Loop rollout_proc14_evt_loop terminating... -[2023-03-02 18:31:36,473][1041406] Stopping RolloutWorker_w5... -[2023-03-02 18:31:36,474][1041406] Loop rollout_proc5_evt_loop terminating... -[2023-03-02 18:31:36,483][1041348] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000001599_1637376.pth... -[2023-03-02 18:31:36,516][1041470] Weights refcount: 2 0 -[2023-03-02 18:31:36,524][1041470] Stopping InferenceWorker_p0-w0... -[2023-03-02 18:31:36,525][1041470] Loop inference_proc0-0_evt_loop terminating... -[2023-03-02 18:31:36,599][1041348] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth -[2023-03-02 18:31:36,603][1041348] Stopping LearnerWorker_p0... -[2023-03-02 18:31:36,603][1041348] Loop learner_proc0_evt_loop terminating... -[2023-03-02 18:32:22,274][1045180] Saving configuration to /home/qgallouedec/train_dir/default_experiment/config.json... -[2023-03-02 18:32:22,275][1045180] Rollout worker 0 uses device cpu -[2023-03-02 18:32:22,275][1045180] Rollout worker 1 uses device cpu -[2023-03-02 18:32:22,275][1045180] Rollout worker 2 uses device cpu -[2023-03-02 18:32:22,275][1045180] Rollout worker 3 uses device cpu -[2023-03-02 18:32:22,275][1045180] Rollout worker 4 uses device cpu -[2023-03-02 18:32:22,275][1045180] Rollout worker 5 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 6 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 7 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 8 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 9 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 10 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 11 uses device cpu -[2023-03-02 18:32:22,276][1045180] Rollout worker 12 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 13 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 14 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 15 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 16 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 17 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 18 uses device cpu -[2023-03-02 18:32:22,277][1045180] Rollout worker 19 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 20 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 21 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 22 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 23 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 24 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 25 uses device cpu -[2023-03-02 18:32:22,278][1045180] Rollout worker 26 uses device cpu -[2023-03-02 18:32:22,279][1045180] Rollout worker 27 uses device cpu -[2023-03-02 18:32:22,279][1045180] Rollout worker 28 uses device cpu -[2023-03-02 18:32:22,279][1045180] Rollout worker 29 uses device cpu -[2023-03-02 18:32:22,279][1045180] Rollout worker 30 uses device cpu -[2023-03-02 18:32:22,279][1045180] Rollout worker 31 uses device cpu -[2023-03-02 18:32:22,294][1045180] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:32:22,294][1045180] InferenceWorker_p0-w0: min num requests: 10 -[2023-03-02 18:32:22,360][1045180] Starting all processes... -[2023-03-02 18:32:22,360][1045180] Starting process learner_proc0 -[2023-03-02 18:32:22,410][1045180] Starting all processes... -[2023-03-02 18:32:22,460][1045180] Starting process inference_proc0-0 -[2023-03-02 18:32:22,468][1045180] Starting process rollout_proc0 -[2023-03-02 18:32:22,468][1045180] Starting process rollout_proc1 -[2023-03-02 18:32:22,468][1045180] Starting process rollout_proc2 -[2023-03-02 18:32:22,468][1045180] Starting process rollout_proc3 -[2023-03-02 18:32:22,469][1045180] Starting process rollout_proc4 -[2023-03-02 18:32:22,471][1045180] Starting process rollout_proc5 -[2023-03-02 18:32:22,477][1045180] Starting process rollout_proc6 -[2023-03-02 18:32:22,477][1045180] Starting process rollout_proc7 -[2023-03-02 18:32:22,478][1045180] Starting process rollout_proc8 -[2023-03-02 18:32:22,480][1045180] Starting process rollout_proc9 -[2023-03-02 18:32:22,480][1045180] Starting process rollout_proc10 -[2023-03-02 18:32:22,485][1045180] Starting process rollout_proc11 -[2023-03-02 18:32:22,490][1045180] Starting process rollout_proc12 -[2023-03-02 18:32:22,490][1045180] Starting process rollout_proc13 -[2023-03-02 18:32:22,490][1045180] Starting process rollout_proc14 -[2023-03-02 18:32:22,491][1045180] Starting process rollout_proc15 -[2023-03-02 18:32:22,491][1045180] Starting process rollout_proc16 -[2023-03-02 18:32:22,494][1045180] Starting process rollout_proc17 -[2023-03-02 18:32:22,501][1045180] Starting process rollout_proc18 -[2023-03-02 18:32:22,502][1045180] Starting process rollout_proc19 -[2023-03-02 18:32:22,502][1045180] Starting process rollout_proc20 -[2023-03-02 18:32:22,509][1045180] Starting process rollout_proc21 -[2023-03-02 18:32:22,526][1045180] Starting process rollout_proc22 -[2023-03-02 18:32:22,529][1045180] Starting process rollout_proc23 -[2023-03-02 18:32:22,560][1045180] Starting process rollout_proc24 -[2023-03-02 18:32:22,565][1045180] Starting process rollout_proc25 -[2023-03-02 18:32:22,580][1045180] Starting process rollout_proc26 -[2023-03-02 18:32:22,580][1045180] Starting process rollout_proc27 -[2023-03-02 18:32:22,612][1045180] Starting process rollout_proc28 -[2023-03-02 18:32:22,613][1045180] Starting process rollout_proc29 -[2023-03-02 18:32:22,614][1045180] Starting process rollout_proc30 -[2023-03-02 18:32:22,619][1045180] Starting process rollout_proc31 -[2023-03-02 18:32:24,266][1045448] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:32:24,266][1045448] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-03-02 18:32:24,277][1045448] Num visible devices: 1 -[2023-03-02 18:32:24,332][1045448] WARNING! It is generally recommended to enable Fixed KL loss (https://arxiv.org/pdf/1707.06347.pdf) for continuous action tasks to avoid potential numerical issues. I.e. set --kl_loss_coeff=0.1 -[2023-03-02 18:32:24,333][1045448] Starting seed is not provided -[2023-03-02 18:32:24,333][1045448] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:32:24,333][1045448] Initializing actor-critic model on device cuda:0 -[2023-03-02 18:32:24,333][1045448] RunningMeanStd input shape: (39,) -[2023-03-02 18:32:24,334][1045448] RunningMeanStd input shape: (1,) -[2023-03-02 18:32:24,464][1045448] Created Actor Critic model with architecture: -[2023-03-02 18:32:24,465][1045448] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): MlpEncoder( - (mlp_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ELU) - (2): RecursiveScriptModule(original_name=Linear) - (3): RecursiveScriptModule(original_name=ELU) - ) - ) - ) - ) - (core): ModelCoreRNN( - (core): GRU(512, 512) - ) - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=8, bias=True) - ) -) -[2023-03-02 18:32:24,527][1045507] Worker 6 uses CPU cores [6] -[2023-03-02 18:32:24,616][1045667] Worker 13 uses CPU cores [13] -[2023-03-02 18:32:24,727][1045501] Worker 1 uses CPU cores [1] -[2023-03-02 18:32:24,727][1045665] Worker 9 uses CPU cores [9] -[2023-03-02 18:32:25,022][1045670] Worker 16 uses CPU cores [16] -[2023-03-02 18:32:25,098][1045500] Worker 0 uses CPU cores [0] -[2023-03-02 18:32:25,108][1045998] Worker 25 uses CPU cores [25] -[2023-03-02 18:32:25,259][1045504] Worker 4 uses CPU cores [4] -[2023-03-02 18:32:25,445][1045666] Worker 8 uses CPU cores [8] -[2023-03-02 18:32:25,530][1045933] Worker 27 uses CPU cores [27] -[2023-03-02 18:32:25,534][1045932] Worker 28 uses CPU cores [28] -[2023-03-02 18:32:25,798][1045671] Worker 18 uses CPU cores [18] -[2023-03-02 18:32:25,871][1045499] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:32:25,871][1045499] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-03-02 18:32:25,882][1045499] Num visible devices: 1 -[2023-03-02 18:32:25,953][1045770] Worker 21 uses CPU cores [21] -[2023-03-02 18:32:25,961][1045668] Worker 12 uses CPU cores [12] -[2023-03-02 18:32:26,222][1045664] Worker 11 uses CPU cores [11] -[2023-03-02 18:32:26,223][1045448] Using optimizer -[2023-03-02 18:32:26,223][1045448] Loading state from checkpoint /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000001599_1637376.pth... -[2023-03-02 18:32:26,246][1045448] Loading model from checkpoint -[2023-03-02 18:32:26,263][1045448] Loaded experiment state at self.train_step=1599, self.env_steps=1637376 -[2023-03-02 18:32:26,271][1045448] Initialized policy 0 weights for model version 1599 -[2023-03-02 18:32:26,286][1045448] LearnerWorker_p0 finished initialization! -[2023-03-02 18:32:26,287][1045448] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-03-02 18:32:26,317][1045834] Worker 22 uses CPU cores [22] -[2023-03-02 18:32:26,368][1045499] RunningMeanStd input shape: (39,) -[2023-03-02 18:32:26,368][1045499] RunningMeanStd input shape: (1,) -[2023-03-02 18:32:26,442][1045706] Worker 19 uses CPU cores [19] -[2023-03-02 18:32:26,542][1045738] Worker 20 uses CPU cores [20] -[2023-03-02 18:32:26,576][1045669] Worker 17 uses CPU cores [17] -[2023-03-02 18:32:26,722][1045705] Worker 15 uses CPU cores [15] -[2023-03-02 18:32:26,790][1045502] Worker 2 uses CPU cores [2] -[2023-03-02 18:32:26,835][1045930] Worker 26 uses CPU cores [26] -[2023-03-02 18:32:27,003][1045578] Worker 7 uses CPU cores [7] -[2023-03-02 18:32:27,034][1045929] Worker 24 uses CPU cores [24] -[2023-03-02 18:32:27,262][1045601] Worker 10 uses CPU cores [10] -[2023-03-02 18:32:27,271][1045503] Worker 3 uses CPU cores [3] -[2023-03-02 18:32:27,275][1045180] Inference worker 0-0 is ready! -[2023-03-02 18:32:27,275][1045180] All inference workers are ready! Signal rollout workers to start! -[2023-03-02 18:32:27,458][1046030] Worker 31 uses CPU cores [31] -[2023-03-02 18:32:27,771][1045965] Worker 29 uses CPU cores [29] -[2023-03-02 18:32:27,885][1045897] Worker 23 uses CPU cores [23] -[2023-03-02 18:32:27,910][1045673] Worker 14 uses CPU cores [14] -[2023-03-02 18:32:28,151][1045505] Worker 5 uses CPU cores [5] -[2023-03-02 18:32:28,219][1045997] Worker 30 uses CPU cores [30] -[2023-03-02 18:32:28,652][1045770] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,673][1045578] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,701][1045667] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,827][1045668] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,857][1045834] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,873][1045671] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,888][1045502] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,890][1045930] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,896][1045998] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,897][1045665] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,904][1045706] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,906][1045933] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,913][1045501] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,913][1045669] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,938][1045507] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,940][1045738] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,959][1045929] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,964][1045705] Decorrelating experience for 0 frames... -[2023-03-02 18:32:28,982][1045670] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,004][1045500] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,007][1045666] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,031][1045932] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,059][1045504] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,186][1046030] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,207][1045503] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,215][1045601] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,313][1045180] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 1637376. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-03-02 18:32:29,476][1045965] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,511][1045664] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,675][1045897] Decorrelating experience for 0 frames... -[2023-03-02 18:32:29,822][1045673] Decorrelating experience for 0 frames... -[2023-03-02 18:32:30,126][1045505] Decorrelating experience for 0 frames... -[2023-03-02 18:32:30,214][1045770] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,232][1045578] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,241][1045997] Decorrelating experience for 0 frames... -[2023-03-02 18:32:30,388][1045667] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,404][1045834] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,437][1045930] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,438][1045998] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,460][1045668] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,469][1045671] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,471][1045669] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,471][1045502] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,474][1045706] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,500][1045507] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,537][1045500] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,542][1045501] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,550][1045932] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,575][1045705] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,578][1045933] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,618][1045929] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,645][1045504] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,662][1045666] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,677][1046030] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,681][1045665] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,697][1045503] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,716][1045738] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,727][1045670] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,735][1045601] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,916][1045965] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,938][1045664] Decorrelating experience for 32 frames... -[2023-03-02 18:32:30,944][1045897] Decorrelating experience for 32 frames... -[2023-03-02 18:32:31,067][1045448] Signal inference workers to stop experience collection... -[2023-03-02 18:32:31,071][1045499] InferenceWorker_p0-w0: stopping experience collection -[2023-03-02 18:32:31,250][1045673] Decorrelating experience for 32 frames... -[2023-03-02 18:32:31,274][1045505] Decorrelating experience for 32 frames... -[2023-03-02 18:32:31,344][1045448] Signal inference workers to resume experience collection... -[2023-03-02 18:32:31,345][1045499] InferenceWorker_p0-w0: resuming experience collection -[2023-03-02 18:32:31,510][1045997] Decorrelating experience for 32 frames... -[2023-03-02 18:32:32,593][1045499] Updated weights for policy 0, policy_version 1609 (0.0221) -[2023-03-02 18:32:33,440][1045499] Updated weights for policy 0, policy_version 1619 (0.0007) -[2023-03-02 18:32:34,284][1045499] Updated weights for policy 0, policy_version 1629 (0.0007) -[2023-03-02 18:32:34,313][1045180] Fps is (10 sec: 6144.2, 60 sec: 6144.2, 300 sec: 6144.2). Total num frames: 1668096. Throughput: 0: 3999.1. Samples: 19995. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-03-02 18:32:34,314][1045180] Avg episode reward: [(0, '28.052')] -[2023-03-02 18:32:35,152][1045499] Updated weights for policy 0, policy_version 1639 (0.0006) -[2023-03-02 18:32:35,961][1045499] Updated weights for policy 0, policy_version 1649 (0.0007) -[2023-03-02 18:32:36,806][1045499] Updated weights for policy 0, policy_version 1659 (0.0007) -[2023-03-02 18:32:37,621][1045499] Updated weights for policy 0, policy_version 1669 (0.0006) -[2023-03-02 18:32:38,466][1045499] Updated weights for policy 0, policy_version 1679 (0.0006) -[2023-03-02 18:32:39,291][1045499] Updated weights for policy 0, policy_version 1689 (0.0007) -[2023-03-02 18:32:39,313][1045180] Fps is (10 sec: 9216.1, 60 sec: 9216.1, 300 sec: 9216.1). Total num frames: 1729536. Throughput: 0: 9334.2. Samples: 93341. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:32:39,314][1045180] Avg episode reward: [(0, '31.189')] -[2023-03-02 18:32:40,122][1045499] Updated weights for policy 0, policy_version 1699 (0.0007) -[2023-03-02 18:32:40,969][1045499] Updated weights for policy 0, policy_version 1709 (0.0007) -[2023-03-02 18:32:41,799][1045499] Updated weights for policy 0, policy_version 1719 (0.0007) -[2023-03-02 18:32:42,289][1045180] Heartbeat connected on Batcher_0 -[2023-03-02 18:32:42,291][1045180] Heartbeat connected on LearnerWorker_p0 -[2023-03-02 18:32:42,296][1045180] Heartbeat connected on RolloutWorker_w0 -[2023-03-02 18:32:42,297][1045180] Heartbeat connected on InferenceWorker_p0-w0 -[2023-03-02 18:32:42,298][1045180] Heartbeat connected on RolloutWorker_w1 -[2023-03-02 18:32:42,302][1045180] Heartbeat connected on RolloutWorker_w2 -[2023-03-02 18:32:42,302][1045180] Heartbeat connected on RolloutWorker_w3 -[2023-03-02 18:32:42,307][1045180] Heartbeat connected on RolloutWorker_w4 -[2023-03-02 18:32:42,307][1045180] Heartbeat connected on RolloutWorker_w5 -[2023-03-02 18:32:42,309][1045180] Heartbeat connected on RolloutWorker_w6 -[2023-03-02 18:32:42,311][1045180] Heartbeat connected on RolloutWorker_w7 -[2023-03-02 18:32:42,315][1045180] Heartbeat connected on RolloutWorker_w9 -[2023-03-02 18:32:42,320][1045180] Heartbeat connected on RolloutWorker_w11 -[2023-03-02 18:32:42,321][1045180] Heartbeat connected on RolloutWorker_w12 -[2023-03-02 18:32:42,323][1045180] Heartbeat connected on RolloutWorker_w13 -[2023-03-02 18:32:42,325][1045180] Heartbeat connected on RolloutWorker_w10 -[2023-03-02 18:32:42,326][1045180] Heartbeat connected on RolloutWorker_w14 -[2023-03-02 18:32:42,327][1045180] Heartbeat connected on RolloutWorker_w15 -[2023-03-02 18:32:42,329][1045180] Heartbeat connected on RolloutWorker_w16 -[2023-03-02 18:32:42,330][1045180] Heartbeat connected on RolloutWorker_w8 -[2023-03-02 18:32:42,331][1045180] Heartbeat connected on RolloutWorker_w17 -[2023-03-02 18:32:42,333][1045180] Heartbeat connected on RolloutWorker_w18 -[2023-03-02 18:32:42,336][1045180] Heartbeat connected on RolloutWorker_w19 -[2023-03-02 18:32:42,337][1045180] Heartbeat connected on RolloutWorker_w20 -[2023-03-02 18:32:42,340][1045180] Heartbeat connected on RolloutWorker_w22 -[2023-03-02 18:32:42,342][1045180] Heartbeat connected on RolloutWorker_w21 -[2023-03-02 18:32:42,343][1045180] Heartbeat connected on RolloutWorker_w23 -[2023-03-02 18:32:42,345][1045180] Heartbeat connected on RolloutWorker_w24 -[2023-03-02 18:32:42,346][1045180] Heartbeat connected on RolloutWorker_w25 -[2023-03-02 18:32:42,348][1045180] Heartbeat connected on RolloutWorker_w26 -[2023-03-02 18:32:42,352][1045180] Heartbeat connected on RolloutWorker_w27 -[2023-03-02 18:32:42,353][1045180] Heartbeat connected on RolloutWorker_w28 -[2023-03-02 18:32:42,354][1045180] Heartbeat connected on RolloutWorker_w29 -[2023-03-02 18:32:42,357][1045180] Heartbeat connected on RolloutWorker_w30 -[2023-03-02 18:32:42,358][1045180] Heartbeat connected on RolloutWorker_w31 -[2023-03-02 18:32:42,660][1045499] Updated weights for policy 0, policy_version 1729 (0.0006) -[2023-03-02 18:32:43,492][1045499] Updated weights for policy 0, policy_version 1739 (0.0006) -[2023-03-02 18:32:44,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 10240.1, 300 sec: 10240.1). Total num frames: 1790976. Throughput: 0: 8660.7. Samples: 129910. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:32:44,314][1045180] Avg episode reward: [(0, '27.934')] -[2023-03-02 18:32:44,315][1045499] Updated weights for policy 0, policy_version 1749 (0.0007) -[2023-03-02 18:32:45,142][1045499] Updated weights for policy 0, policy_version 1759 (0.0007) -[2023-03-02 18:32:45,969][1045499] Updated weights for policy 0, policy_version 1769 (0.0006) -[2023-03-02 18:32:46,800][1045499] Updated weights for policy 0, policy_version 1779 (0.0007) -[2023-03-02 18:32:47,637][1045499] Updated weights for policy 0, policy_version 1789 (0.0008) -[2023-03-02 18:32:48,459][1045499] Updated weights for policy 0, policy_version 1799 (0.0006) -[2023-03-02 18:32:49,262][1045499] Updated weights for policy 0, policy_version 1809 (0.0007) -[2023-03-02 18:32:49,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 10752.1, 300 sec: 10752.1). Total num frames: 1852416. Throughput: 0: 10205.5. Samples: 204110. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:32:49,314][1045180] Avg episode reward: [(0, '26.200')] -[2023-03-02 18:32:50,097][1045499] Updated weights for policy 0, policy_version 1819 (0.0007) -[2023-03-02 18:32:50,900][1045499] Updated weights for policy 0, policy_version 1829 (0.0006) -[2023-03-02 18:32:51,717][1045499] Updated weights for policy 0, policy_version 1839 (0.0007) -[2023-03-02 18:32:52,571][1045499] Updated weights for policy 0, policy_version 1849 (0.0008) -[2023-03-02 18:32:53,403][1045499] Updated weights for policy 0, policy_version 1859 (0.0006) -[2023-03-02 18:32:54,275][1045499] Updated weights for policy 0, policy_version 1869 (0.0006) -[2023-03-02 18:32:54,313][1045180] Fps is (10 sec: 12287.8, 60 sec: 11059.2, 300 sec: 11059.2). Total num frames: 1913856. Throughput: 0: 11121.8. Samples: 278046. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:32:54,314][1045180] Avg episode reward: [(0, '27.038')] -[2023-03-02 18:32:55,144][1045499] Updated weights for policy 0, policy_version 1879 (0.0007) -[2023-03-02 18:32:55,959][1045499] Updated weights for policy 0, policy_version 1889 (0.0006) -[2023-03-02 18:32:56,821][1045499] Updated weights for policy 0, policy_version 1899 (0.0007) -[2023-03-02 18:32:57,656][1045499] Updated weights for policy 0, policy_version 1909 (0.0007) -[2023-03-02 18:32:58,479][1045499] Updated weights for policy 0, policy_version 1919 (0.0007) -[2023-03-02 18:32:59,311][1045499] Updated weights for policy 0, policy_version 1929 (0.0007) -[2023-03-02 18:32:59,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 11264.0, 300 sec: 11264.0). Total num frames: 1975296. Throughput: 0: 10472.7. Samples: 314181. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:32:59,314][1045180] Avg episode reward: [(0, '30.690')] -[2023-03-02 18:33:00,170][1045499] Updated weights for policy 0, policy_version 1939 (0.0007) -[2023-03-02 18:33:00,999][1045499] Updated weights for policy 0, policy_version 1949 (0.0008) -[2023-03-02 18:33:01,827][1045499] Updated weights for policy 0, policy_version 1959 (0.0007) -[2023-03-02 18:33:02,642][1045499] Updated weights for policy 0, policy_version 1969 (0.0007) -[2023-03-02 18:33:03,507][1045499] Updated weights for policy 0, policy_version 1979 (0.0006) -[2023-03-02 18:33:04,313][1045180] Fps is (10 sec: 12185.7, 60 sec: 11381.0, 300 sec: 11381.0). Total num frames: 2035712. Throughput: 0: 11079.9. Samples: 387797. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:33:04,314][1045180] Avg episode reward: [(0, '41.201')] -[2023-03-02 18:33:04,314][1045448] Saving new best policy, reward=41.201! -[2023-03-02 18:33:04,369][1045499] Updated weights for policy 0, policy_version 1989 (0.0006) -[2023-03-02 18:33:05,165][1045499] Updated weights for policy 0, policy_version 1999 (0.0006) -[2023-03-02 18:33:05,991][1045499] Updated weights for policy 0, policy_version 2009 (0.0007) -[2023-03-02 18:33:06,863][1045499] Updated weights for policy 0, policy_version 2019 (0.0006) -[2023-03-02 18:33:07,660][1045499] Updated weights for policy 0, policy_version 2029 (0.0006) -[2023-03-02 18:33:08,507][1045499] Updated weights for policy 0, policy_version 2039 (0.0006) -[2023-03-02 18:33:09,313][1045180] Fps is (10 sec: 12185.4, 60 sec: 11494.4, 300 sec: 11494.4). Total num frames: 2097152. Throughput: 0: 11538.3. Samples: 461533. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:33:09,314][1045180] Avg episode reward: [(0, '40.773')] -[2023-03-02 18:33:09,322][1045499] Updated weights for policy 0, policy_version 2049 (0.0008) -[2023-03-02 18:33:10,151][1045499] Updated weights for policy 0, policy_version 2059 (0.0007) -[2023-03-02 18:33:10,984][1045499] Updated weights for policy 0, policy_version 2069 (0.0007) -[2023-03-02 18:33:11,809][1045499] Updated weights for policy 0, policy_version 2079 (0.0007) -[2023-03-02 18:33:12,638][1045499] Updated weights for policy 0, policy_version 2089 (0.0007) -[2023-03-02 18:33:13,490][1045499] Updated weights for policy 0, policy_version 2099 (0.0007) -[2023-03-02 18:33:14,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 11582.6, 300 sec: 11582.6). Total num frames: 2158592. Throughput: 0: 11080.8. Samples: 498637. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:33:14,314][1045180] Avg episode reward: [(0, '27.381')] -[2023-03-02 18:33:14,317][1045499] Updated weights for policy 0, policy_version 2109 (0.0006) -[2023-03-02 18:33:15,138][1045499] Updated weights for policy 0, policy_version 2119 (0.0007) -[2023-03-02 18:33:15,965][1045499] Updated weights for policy 0, policy_version 2129 (0.0006) -[2023-03-02 18:33:16,792][1045499] Updated weights for policy 0, policy_version 2139 (0.0007) -[2023-03-02 18:33:17,635][1045499] Updated weights for policy 0, policy_version 2149 (0.0009) -[2023-03-02 18:33:18,464][1045499] Updated weights for policy 0, policy_version 2159 (0.0007) -[2023-03-02 18:33:19,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 11653.1, 300 sec: 11653.1). Total num frames: 2220032. Throughput: 0: 12273.1. Samples: 572287. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:19,314][1045180] Avg episode reward: [(0, '33.109')] -[2023-03-02 18:33:19,327][1045499] Updated weights for policy 0, policy_version 2169 (0.0007) -[2023-03-02 18:33:20,138][1045499] Updated weights for policy 0, policy_version 2179 (0.0006) -[2023-03-02 18:33:20,983][1045499] Updated weights for policy 0, policy_version 2189 (0.0007) -[2023-03-02 18:33:21,812][1045499] Updated weights for policy 0, policy_version 2199 (0.0007) -[2023-03-02 18:33:22,645][1045499] Updated weights for policy 0, policy_version 2209 (0.0006) -[2023-03-02 18:33:23,468][1045499] Updated weights for policy 0, policy_version 2219 (0.0007) -[2023-03-02 18:33:24,308][1045499] Updated weights for policy 0, policy_version 2229 (0.0007) -[2023-03-02 18:33:24,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 11729.5, 300 sec: 11729.5). Total num frames: 2282496. Throughput: 0: 12281.5. Samples: 646009. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:33:24,314][1045180] Avg episode reward: [(0, '34.832')] -[2023-03-02 18:33:25,126][1045499] Updated weights for policy 0, policy_version 2239 (0.0006) -[2023-03-02 18:33:25,922][1045499] Updated weights for policy 0, policy_version 2249 (0.0007) -[2023-03-02 18:33:26,781][1045499] Updated weights for policy 0, policy_version 2259 (0.0006) -[2023-03-02 18:33:27,583][1045499] Updated weights for policy 0, policy_version 2269 (0.0008) -[2023-03-02 18:33:28,417][1045499] Updated weights for policy 0, policy_version 2279 (0.0006) -[2023-03-02 18:33:29,245][1045499] Updated weights for policy 0, policy_version 2289 (0.0007) -[2023-03-02 18:33:29,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 11776.0, 300 sec: 11776.0). Total num frames: 2343936. Throughput: 0: 12302.3. Samples: 683514. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:29,314][1045180] Avg episode reward: [(0, '29.408')] -[2023-03-02 18:33:30,083][1045499] Updated weights for policy 0, policy_version 2299 (0.0006) -[2023-03-02 18:33:30,917][1045499] Updated weights for policy 0, policy_version 2309 (0.0007) -[2023-03-02 18:33:31,777][1045499] Updated weights for policy 0, policy_version 2319 (0.0006) -[2023-03-02 18:33:32,603][1045499] Updated weights for policy 0, policy_version 2329 (0.0006) -[2023-03-02 18:33:33,417][1045499] Updated weights for policy 0, policy_version 2339 (0.0007) -[2023-03-02 18:33:34,264][1045499] Updated weights for policy 0, policy_version 2349 (0.0008) -[2023-03-02 18:33:34,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11815.4). Total num frames: 2405376. Throughput: 0: 12292.6. Samples: 757280. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:34,314][1045180] Avg episode reward: [(0, '30.578')] -[2023-03-02 18:33:35,086][1045499] Updated weights for policy 0, policy_version 2359 (0.0006) -[2023-03-02 18:33:35,899][1045499] Updated weights for policy 0, policy_version 2369 (0.0007) -[2023-03-02 18:33:36,741][1045499] Updated weights for policy 0, policy_version 2379 (0.0007) -[2023-03-02 18:33:37,546][1045499] Updated weights for policy 0, policy_version 2389 (0.0007) -[2023-03-02 18:33:38,362][1045499] Updated weights for policy 0, policy_version 2399 (0.0006) -[2023-03-02 18:33:39,236][1045499] Updated weights for policy 0, policy_version 2409 (0.0007) -[2023-03-02 18:33:39,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11849.2). Total num frames: 2466816. Throughput: 0: 12294.8. Samples: 831309. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:33:39,314][1045180] Avg episode reward: [(0, '34.766')] -[2023-03-02 18:33:40,028][1045499] Updated weights for policy 0, policy_version 2419 (0.0006) -[2023-03-02 18:33:40,840][1045499] Updated weights for policy 0, policy_version 2429 (0.0007) -[2023-03-02 18:33:41,676][1045499] Updated weights for policy 0, policy_version 2439 (0.0007) -[2023-03-02 18:33:42,504][1045499] Updated weights for policy 0, policy_version 2449 (0.0006) -[2023-03-02 18:33:43,318][1045499] Updated weights for policy 0, policy_version 2459 (0.0006) -[2023-03-02 18:33:44,148][1045499] Updated weights for policy 0, policy_version 2469 (0.0006) -[2023-03-02 18:33:44,313][1045180] Fps is (10 sec: 12492.9, 60 sec: 12322.1, 300 sec: 11905.7). Total num frames: 2530304. Throughput: 0: 12329.4. Samples: 869003. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:44,314][1045180] Avg episode reward: [(0, '36.567')] -[2023-03-02 18:33:44,967][1045499] Updated weights for policy 0, policy_version 2479 (0.0007) -[2023-03-02 18:33:45,777][1045499] Updated weights for policy 0, policy_version 2489 (0.0006) -[2023-03-02 18:33:46,618][1045499] Updated weights for policy 0, policy_version 2499 (0.0006) -[2023-03-02 18:33:47,439][1045499] Updated weights for policy 0, policy_version 2509 (0.0007) -[2023-03-02 18:33:48,277][1045499] Updated weights for policy 0, policy_version 2519 (0.0007) -[2023-03-02 18:33:49,092][1045499] Updated weights for policy 0, policy_version 2529 (0.0007) -[2023-03-02 18:33:49,313][1045180] Fps is (10 sec: 12492.9, 60 sec: 12322.1, 300 sec: 11929.6). Total num frames: 2591744. Throughput: 0: 12347.2. Samples: 943419. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:49,314][1045180] Avg episode reward: [(0, '43.631')] -[2023-03-02 18:33:49,317][1045448] Saving new best policy, reward=43.631! -[2023-03-02 18:33:49,950][1045499] Updated weights for policy 0, policy_version 2539 (0.0006) -[2023-03-02 18:33:50,777][1045499] Updated weights for policy 0, policy_version 2549 (0.0006) -[2023-03-02 18:33:51,598][1045499] Updated weights for policy 0, policy_version 2559 (0.0007) -[2023-03-02 18:33:52,422][1045499] Updated weights for policy 0, policy_version 2569 (0.0006) -[2023-03-02 18:33:53,256][1045499] Updated weights for policy 0, policy_version 2579 (0.0007) -[2023-03-02 18:33:54,073][1045499] Updated weights for policy 0, policy_version 2589 (0.0006) -[2023-03-02 18:33:54,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12322.2, 300 sec: 11950.7). Total num frames: 2653184. Throughput: 0: 12355.4. Samples: 1017525. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:33:54,314][1045180] Avg episode reward: [(0, '77.508')] -[2023-03-02 18:33:54,314][1045448] Saving new best policy, reward=77.508! -[2023-03-02 18:33:54,892][1045499] Updated weights for policy 0, policy_version 2599 (0.0007) -[2023-03-02 18:33:55,719][1045499] Updated weights for policy 0, policy_version 2609 (0.0006) -[2023-03-02 18:33:56,543][1045499] Updated weights for policy 0, policy_version 2619 (0.0006) -[2023-03-02 18:33:57,385][1045499] Updated weights for policy 0, policy_version 2629 (0.0007) -[2023-03-02 18:33:58,252][1045499] Updated weights for policy 0, policy_version 2639 (0.0007) -[2023-03-02 18:33:59,071][1045499] Updated weights for policy 0, policy_version 2649 (0.0006) -[2023-03-02 18:33:59,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12339.2, 300 sec: 11980.8). Total num frames: 2715648. Throughput: 0: 12353.1. Samples: 1054528. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0) -[2023-03-02 18:33:59,314][1045180] Avg episode reward: [(0, '74.012')] -[2023-03-02 18:33:59,877][1045499] Updated weights for policy 0, policy_version 2659 (0.0008) -[2023-03-02 18:34:00,713][1045499] Updated weights for policy 0, policy_version 2669 (0.0007) -[2023-03-02 18:34:01,538][1045499] Updated weights for policy 0, policy_version 2679 (0.0006) -[2023-03-02 18:34:02,368][1045499] Updated weights for policy 0, policy_version 2689 (0.0007) -[2023-03-02 18:34:03,168][1045499] Updated weights for policy 0, policy_version 2699 (0.0006) -[2023-03-02 18:34:03,985][1045499] Updated weights for policy 0, policy_version 2709 (0.0006) -[2023-03-02 18:34:04,313][1045180] Fps is (10 sec: 12492.7, 60 sec: 12373.3, 300 sec: 12007.8). Total num frames: 2778112. Throughput: 0: 12371.6. Samples: 1129007. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:04,314][1045180] Avg episode reward: [(0, '75.130')] -[2023-03-02 18:34:04,834][1045499] Updated weights for policy 0, policy_version 2719 (0.0008) -[2023-03-02 18:34:05,669][1045499] Updated weights for policy 0, policy_version 2729 (0.0007) -[2023-03-02 18:34:06,490][1045499] Updated weights for policy 0, policy_version 2739 (0.0006) -[2023-03-02 18:34:07,330][1045499] Updated weights for policy 0, policy_version 2749 (0.0006) -[2023-03-02 18:34:08,156][1045499] Updated weights for policy 0, policy_version 2759 (0.0006) -[2023-03-02 18:34:09,004][1045499] Updated weights for policy 0, policy_version 2769 (0.0007) -[2023-03-02 18:34:09,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12011.5). Total num frames: 2838528. Throughput: 0: 12374.0. Samples: 1202839. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:09,314][1045180] Avg episode reward: [(0, '79.370')] -[2023-03-02 18:34:09,328][1045448] Saving new best policy, reward=79.370! -[2023-03-02 18:34:09,816][1045499] Updated weights for policy 0, policy_version 2779 (0.0008) -[2023-03-02 18:34:10,675][1045499] Updated weights for policy 0, policy_version 2789 (0.0007) -[2023-03-02 18:34:11,495][1045499] Updated weights for policy 0, policy_version 2799 (0.0006) -[2023-03-02 18:34:12,316][1045499] Updated weights for policy 0, policy_version 2809 (0.0006) -[2023-03-02 18:34:13,151][1045499] Updated weights for policy 0, policy_version 2819 (0.0006) -[2023-03-02 18:34:13,969][1045499] Updated weights for policy 0, policy_version 2829 (0.0007) -[2023-03-02 18:34:14,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12373.4, 300 sec: 12034.5). Total num frames: 2900992. Throughput: 0: 12362.2. Samples: 1239811. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:14,314][1045180] Avg episode reward: [(0, '32.061')] -[2023-03-02 18:34:14,802][1045499] Updated weights for policy 0, policy_version 2839 (0.0006) -[2023-03-02 18:34:15,643][1045499] Updated weights for policy 0, policy_version 2849 (0.0006) -[2023-03-02 18:34:16,488][1045499] Updated weights for policy 0, policy_version 2859 (0.0006) -[2023-03-02 18:34:17,317][1045499] Updated weights for policy 0, policy_version 2869 (0.0006) -[2023-03-02 18:34:18,128][1045499] Updated weights for policy 0, policy_version 2879 (0.0006) -[2023-03-02 18:34:18,947][1045499] Updated weights for policy 0, policy_version 2889 (0.0006) -[2023-03-02 18:34:19,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12046.0). Total num frames: 2962432. Throughput: 0: 12373.8. Samples: 1314102. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:19,314][1045180] Avg episode reward: [(0, '88.601')] -[2023-03-02 18:34:19,331][1045448] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000002894_2963456.pth... -[2023-03-02 18:34:19,362][1045448] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000001277_1307648.pth -[2023-03-02 18:34:19,365][1045448] Saving new best policy, reward=88.601! -[2023-03-02 18:34:19,768][1045499] Updated weights for policy 0, policy_version 2899 (0.0007) -[2023-03-02 18:34:20,599][1045499] Updated weights for policy 0, policy_version 2909 (0.0006) -[2023-03-02 18:34:21,415][1045499] Updated weights for policy 0, policy_version 2919 (0.0008) -[2023-03-02 18:34:22,239][1045499] Updated weights for policy 0, policy_version 2929 (0.0007) -[2023-03-02 18:34:23,070][1045499] Updated weights for policy 0, policy_version 2939 (0.0007) -[2023-03-02 18:34:23,915][1045499] Updated weights for policy 0, policy_version 2949 (0.0007) -[2023-03-02 18:34:24,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12056.5). Total num frames: 3023872. Throughput: 0: 12377.1. Samples: 1388276. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:34:24,314][1045180] Avg episode reward: [(0, '97.890')] -[2023-03-02 18:34:24,322][1045448] Saving new best policy, reward=97.890! -[2023-03-02 18:34:24,749][1045499] Updated weights for policy 0, policy_version 2959 (0.0007) -[2023-03-02 18:34:25,556][1045499] Updated weights for policy 0, policy_version 2969 (0.0007) -[2023-03-02 18:34:26,376][1045499] Updated weights for policy 0, policy_version 2979 (0.0007) -[2023-03-02 18:34:27,231][1045499] Updated weights for policy 0, policy_version 2989 (0.0008) -[2023-03-02 18:34:28,077][1045499] Updated weights for policy 0, policy_version 2999 (0.0006) -[2023-03-02 18:34:28,905][1045499] Updated weights for policy 0, policy_version 3009 (0.0006) -[2023-03-02 18:34:29,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12066.1). Total num frames: 3085312. Throughput: 0: 12361.4. Samples: 1425267. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:29,314][1045180] Avg episode reward: [(0, '100.699')] -[2023-03-02 18:34:29,325][1045448] Saving new best policy, reward=100.699! -[2023-03-02 18:34:29,726][1045499] Updated weights for policy 0, policy_version 3019 (0.0006) -[2023-03-02 18:34:30,577][1045499] Updated weights for policy 0, policy_version 3029 (0.0006) -[2023-03-02 18:34:31,391][1045499] Updated weights for policy 0, policy_version 3039 (0.0006) -[2023-03-02 18:34:32,226][1045499] Updated weights for policy 0, policy_version 3049 (0.0007) -[2023-03-02 18:34:33,077][1045499] Updated weights for policy 0, policy_version 3059 (0.0007) -[2023-03-02 18:34:33,917][1045499] Updated weights for policy 0, policy_version 3069 (0.0008) -[2023-03-02 18:34:34,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12075.0). Total num frames: 3146752. Throughput: 0: 12339.6. Samples: 1498704. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:34:34,314][1045180] Avg episode reward: [(0, '149.621')] -[2023-03-02 18:34:34,314][1045448] Saving new best policy, reward=149.621! -[2023-03-02 18:34:34,733][1045499] Updated weights for policy 0, policy_version 3079 (0.0007) -[2023-03-02 18:34:35,554][1045499] Updated weights for policy 0, policy_version 3089 (0.0007) -[2023-03-02 18:34:36,387][1045499] Updated weights for policy 0, policy_version 3099 (0.0007) -[2023-03-02 18:34:37,192][1045499] Updated weights for policy 0, policy_version 3109 (0.0007) -[2023-03-02 18:34:38,002][1045499] Updated weights for policy 0, policy_version 3119 (0.0007) -[2023-03-02 18:34:38,820][1045499] Updated weights for policy 0, policy_version 3129 (0.0007) -[2023-03-02 18:34:39,313][1045180] Fps is (10 sec: 12390.2, 60 sec: 12373.3, 300 sec: 12091.1). Total num frames: 3209216. Throughput: 0: 12356.9. Samples: 1573586. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:34:39,314][1045180] Avg episode reward: [(0, '172.615')] -[2023-03-02 18:34:39,326][1045448] Saving new best policy, reward=172.615! -[2023-03-02 18:34:39,661][1045499] Updated weights for policy 0, policy_version 3139 (0.0006) -[2023-03-02 18:34:40,492][1045499] Updated weights for policy 0, policy_version 3149 (0.0007) -[2023-03-02 18:34:41,338][1045499] Updated weights for policy 0, policy_version 3159 (0.0007) -[2023-03-02 18:34:42,192][1045499] Updated weights for policy 0, policy_version 3169 (0.0008) -[2023-03-02 18:34:43,043][1045499] Updated weights for policy 0, policy_version 3179 (0.0007) -[2023-03-02 18:34:43,880][1045499] Updated weights for policy 0, policy_version 3189 (0.0007) -[2023-03-02 18:34:44,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12339.2, 300 sec: 12098.4). Total num frames: 3270656. Throughput: 0: 12346.9. Samples: 1610137. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:34:44,314][1045180] Avg episode reward: [(0, '90.885')] -[2023-03-02 18:34:44,732][1045499] Updated weights for policy 0, policy_version 3199 (0.0006) -[2023-03-02 18:34:45,538][1045499] Updated weights for policy 0, policy_version 3209 (0.0007) -[2023-03-02 18:34:46,358][1045499] Updated weights for policy 0, policy_version 3219 (0.0007) -[2023-03-02 18:34:47,186][1045499] Updated weights for policy 0, policy_version 3229 (0.0007) -[2023-03-02 18:34:48,024][1045499] Updated weights for policy 0, policy_version 3239 (0.0007) -[2023-03-02 18:34:48,850][1045499] Updated weights for policy 0, policy_version 3249 (0.0006) -[2023-03-02 18:34:49,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12339.2, 300 sec: 12105.1). Total num frames: 3332096. Throughput: 0: 12327.9. Samples: 1683764. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:34:49,314][1045180] Avg episode reward: [(0, '91.447')] -[2023-03-02 18:34:49,672][1045499] Updated weights for policy 0, policy_version 3259 (0.0007) -[2023-03-02 18:34:50,526][1045499] Updated weights for policy 0, policy_version 3269 (0.0007) -[2023-03-02 18:34:51,351][1045499] Updated weights for policy 0, policy_version 3279 (0.0007) -[2023-03-02 18:34:52,177][1045499] Updated weights for policy 0, policy_version 3289 (0.0008) -[2023-03-02 18:34:52,982][1045499] Updated weights for policy 0, policy_version 3299 (0.0007) -[2023-03-02 18:34:53,826][1045499] Updated weights for policy 0, policy_version 3309 (0.0007) -[2023-03-02 18:34:54,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12339.2, 300 sec: 12111.5). Total num frames: 3393536. Throughput: 0: 12332.9. Samples: 1757821. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:34:54,314][1045180] Avg episode reward: [(0, '58.689')] -[2023-03-02 18:34:54,646][1045499] Updated weights for policy 0, policy_version 3319 (0.0007) -[2023-03-02 18:34:55,469][1045499] Updated weights for policy 0, policy_version 3329 (0.0007) -[2023-03-02 18:34:56,294][1045499] Updated weights for policy 0, policy_version 3339 (0.0007) -[2023-03-02 18:34:57,112][1045499] Updated weights for policy 0, policy_version 3349 (0.0007) -[2023-03-02 18:34:57,991][1045499] Updated weights for policy 0, policy_version 3359 (0.0008) -[2023-03-02 18:34:58,813][1045499] Updated weights for policy 0, policy_version 3369 (0.0006) -[2023-03-02 18:34:59,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12322.1, 300 sec: 12117.3). Total num frames: 3454976. Throughput: 0: 12341.4. Samples: 1795176. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:34:59,314][1045180] Avg episode reward: [(0, '78.526')] -[2023-03-02 18:34:59,641][1045499] Updated weights for policy 0, policy_version 3379 (0.0006) -[2023-03-02 18:35:00,470][1045499] Updated weights for policy 0, policy_version 3389 (0.0006) -[2023-03-02 18:35:01,276][1045499] Updated weights for policy 0, policy_version 3399 (0.0007) -[2023-03-02 18:35:02,108][1045499] Updated weights for policy 0, policy_version 3409 (0.0007) -[2023-03-02 18:35:02,935][1045499] Updated weights for policy 0, policy_version 3419 (0.0009) -[2023-03-02 18:35:03,814][1045499] Updated weights for policy 0, policy_version 3429 (0.0007) -[2023-03-02 18:35:04,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12305.1, 300 sec: 12122.8). Total num frames: 3516416. Throughput: 0: 12331.7. Samples: 1869030. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:04,314][1045180] Avg episode reward: [(0, '37.692')] -[2023-03-02 18:35:04,667][1045499] Updated weights for policy 0, policy_version 3439 (0.0008) -[2023-03-02 18:35:05,503][1045499] Updated weights for policy 0, policy_version 3449 (0.0007) -[2023-03-02 18:35:06,332][1045499] Updated weights for policy 0, policy_version 3459 (0.0007) -[2023-03-02 18:35:07,173][1045499] Updated weights for policy 0, policy_version 3469 (0.0006) -[2023-03-02 18:35:07,988][1045499] Updated weights for policy 0, policy_version 3479 (0.0007) -[2023-03-02 18:35:08,793][1045499] Updated weights for policy 0, policy_version 3489 (0.0007) -[2023-03-02 18:35:09,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12339.2, 300 sec: 12134.4). Total num frames: 3578880. Throughput: 0: 12318.8. Samples: 1942621. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:35:09,314][1045180] Avg episode reward: [(0, '16.756')] -[2023-03-02 18:35:09,617][1045499] Updated weights for policy 0, policy_version 3499 (0.0007) -[2023-03-02 18:35:10,447][1045499] Updated weights for policy 0, policy_version 3509 (0.0007) -[2023-03-02 18:35:11,273][1045499] Updated weights for policy 0, policy_version 3519 (0.0007) -[2023-03-02 18:35:12,092][1045499] Updated weights for policy 0, policy_version 3529 (0.0006) -[2023-03-02 18:35:12,933][1045499] Updated weights for policy 0, policy_version 3539 (0.0007) -[2023-03-02 18:35:13,795][1045499] Updated weights for policy 0, policy_version 3549 (0.0007) -[2023-03-02 18:35:14,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12322.1, 300 sec: 12139.1). Total num frames: 3640320. Throughput: 0: 12320.7. Samples: 1979700. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:14,314][1045180] Avg episode reward: [(0, '15.795')] -[2023-03-02 18:35:14,619][1045499] Updated weights for policy 0, policy_version 3559 (0.0006) -[2023-03-02 18:35:15,460][1045499] Updated weights for policy 0, policy_version 3569 (0.0006) -[2023-03-02 18:35:16,285][1045499] Updated weights for policy 0, policy_version 3579 (0.0007) -[2023-03-02 18:35:17,097][1045499] Updated weights for policy 0, policy_version 3589 (0.0006) -[2023-03-02 18:35:17,956][1045499] Updated weights for policy 0, policy_version 3599 (0.0006) -[2023-03-02 18:35:18,785][1045499] Updated weights for policy 0, policy_version 3609 (0.0007) -[2023-03-02 18:35:19,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12322.1, 300 sec: 12143.4). Total num frames: 3701760. Throughput: 0: 12321.7. Samples: 2053180. Policy #0 lag: (min: 0.0, avg: 1.5, max: 3.0) -[2023-03-02 18:35:19,314][1045180] Avg episode reward: [(0, '24.007')] -[2023-03-02 18:35:19,607][1045499] Updated weights for policy 0, policy_version 3619 (0.0006) -[2023-03-02 18:35:20,448][1045499] Updated weights for policy 0, policy_version 3629 (0.0006) -[2023-03-02 18:35:21,280][1045499] Updated weights for policy 0, policy_version 3639 (0.0008) -[2023-03-02 18:35:22,112][1045499] Updated weights for policy 0, policy_version 3649 (0.0006) -[2023-03-02 18:35:22,956][1045499] Updated weights for policy 0, policy_version 3659 (0.0007) -[2023-03-02 18:35:23,781][1045499] Updated weights for policy 0, policy_version 3669 (0.0007) -[2023-03-02 18:35:24,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12322.1, 300 sec: 12147.6). Total num frames: 3763200. Throughput: 0: 12293.7. Samples: 2126801. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:24,314][1045180] Avg episode reward: [(0, '15.563')] -[2023-03-02 18:35:24,657][1045499] Updated weights for policy 0, policy_version 3679 (0.0007) -[2023-03-02 18:35:25,480][1045499] Updated weights for policy 0, policy_version 3689 (0.0006) -[2023-03-02 18:35:26,302][1045499] Updated weights for policy 0, policy_version 3699 (0.0007) -[2023-03-02 18:35:27,165][1045499] Updated weights for policy 0, policy_version 3709 (0.0006) -[2023-03-02 18:35:27,976][1045499] Updated weights for policy 0, policy_version 3719 (0.0006) -[2023-03-02 18:35:28,839][1045499] Updated weights for policy 0, policy_version 3729 (0.0007) -[2023-03-02 18:35:29,313][1045180] Fps is (10 sec: 12185.7, 60 sec: 12305.1, 300 sec: 12145.8). Total num frames: 3823616. Throughput: 0: 12290.8. Samples: 2163221. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:29,314][1045180] Avg episode reward: [(0, '17.900')] -[2023-03-02 18:35:29,683][1045499] Updated weights for policy 0, policy_version 3739 (0.0007) -[2023-03-02 18:35:30,500][1045499] Updated weights for policy 0, policy_version 3749 (0.0006) -[2023-03-02 18:35:31,301][1045499] Updated weights for policy 0, policy_version 3759 (0.0007) -[2023-03-02 18:35:32,123][1045499] Updated weights for policy 0, policy_version 3769 (0.0007) -[2023-03-02 18:35:32,944][1045499] Updated weights for policy 0, policy_version 3779 (0.0007) -[2023-03-02 18:35:33,776][1045499] Updated weights for policy 0, policy_version 3789 (0.0007) -[2023-03-02 18:35:34,313][1045180] Fps is (10 sec: 12287.8, 60 sec: 12322.1, 300 sec: 12155.2). Total num frames: 3886080. Throughput: 0: 12306.8. Samples: 2237568. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:35:34,314][1045180] Avg episode reward: [(0, '24.087')] -[2023-03-02 18:35:34,595][1045499] Updated weights for policy 0, policy_version 3799 (0.0007) -[2023-03-02 18:35:35,453][1045499] Updated weights for policy 0, policy_version 3809 (0.0006) -[2023-03-02 18:35:36,262][1045499] Updated weights for policy 0, policy_version 3819 (0.0007) -[2023-03-02 18:35:37,081][1045499] Updated weights for policy 0, policy_version 3829 (0.0007) -[2023-03-02 18:35:37,911][1045499] Updated weights for policy 0, policy_version 3839 (0.0007) -[2023-03-02 18:35:38,564][1045448] KL-divergence is very high: 173.6769 -[2023-03-02 18:35:38,745][1045499] Updated weights for policy 0, policy_version 3849 (0.0007) -[2023-03-02 18:35:39,314][1045180] Fps is (10 sec: 12492.1, 60 sec: 12322.0, 300 sec: 12164.0). Total num frames: 3948544. Throughput: 0: 12318.6. Samples: 2312164. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:39,314][1045180] Avg episode reward: [(0, '16.004')] -[2023-03-02 18:35:39,545][1045499] Updated weights for policy 0, policy_version 3859 (0.0007) -[2023-03-02 18:35:40,396][1045499] Updated weights for policy 0, policy_version 3869 (0.0006) -[2023-03-02 18:35:41,197][1045499] Updated weights for policy 0, policy_version 3879 (0.0006) -[2023-03-02 18:35:42,048][1045499] Updated weights for policy 0, policy_version 3889 (0.0007) -[2023-03-02 18:35:42,891][1045499] Updated weights for policy 0, policy_version 3899 (0.0007) -[2023-03-02 18:35:43,718][1045499] Updated weights for policy 0, policy_version 3909 (0.0006) -[2023-03-02 18:35:44,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12322.1, 300 sec: 12167.2). Total num frames: 4009984. Throughput: 0: 12306.0. Samples: 2348947. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:44,314][1045180] Avg episode reward: [(0, '25.979')] -[2023-03-02 18:35:44,543][1045499] Updated weights for policy 0, policy_version 3919 (0.0007) -[2023-03-02 18:35:45,376][1045499] Updated weights for policy 0, policy_version 3929 (0.0007) -[2023-03-02 18:35:46,204][1045499] Updated weights for policy 0, policy_version 3939 (0.0006) -[2023-03-02 18:35:47,032][1045499] Updated weights for policy 0, policy_version 3949 (0.0006) -[2023-03-02 18:35:47,866][1045499] Updated weights for policy 0, policy_version 3959 (0.0007) -[2023-03-02 18:35:48,691][1045499] Updated weights for policy 0, policy_version 3969 (0.0007) -[2023-03-02 18:35:49,313][1045180] Fps is (10 sec: 12288.6, 60 sec: 12322.1, 300 sec: 12170.2). Total num frames: 4071424. Throughput: 0: 12310.4. Samples: 2423000. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:49,314][1045180] Avg episode reward: [(0, '31.309')] -[2023-03-02 18:35:49,515][1045499] Updated weights for policy 0, policy_version 3979 (0.0007) -[2023-03-02 18:35:50,353][1045499] Updated weights for policy 0, policy_version 3989 (0.0007) -[2023-03-02 18:35:51,156][1045499] Updated weights for policy 0, policy_version 3999 (0.0007) -[2023-03-02 18:35:51,971][1045499] Updated weights for policy 0, policy_version 4009 (0.0007) -[2023-03-02 18:35:52,797][1045499] Updated weights for policy 0, policy_version 4019 (0.0006) -[2023-03-02 18:35:53,527][1045448] KL-divergence is very high: 147.1295 -[2023-03-02 18:35:53,637][1045499] Updated weights for policy 0, policy_version 4029 (0.0007) -[2023-03-02 18:35:54,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12339.2, 300 sec: 12178.1). Total num frames: 4133888. Throughput: 0: 12337.3. Samples: 2497801. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:35:54,314][1045180] Avg episode reward: [(0, '33.488')] -[2023-03-02 18:35:54,450][1045499] Updated weights for policy 0, policy_version 4039 (0.0006) -[2023-03-02 18:35:55,250][1045499] Updated weights for policy 0, policy_version 4049 (0.0007) -[2023-03-02 18:35:56,091][1045499] Updated weights for policy 0, policy_version 4059 (0.0006) -[2023-03-02 18:35:56,910][1045499] Updated weights for policy 0, policy_version 4069 (0.0007) -[2023-03-02 18:35:57,722][1045499] Updated weights for policy 0, policy_version 4079 (0.0007) -[2023-03-02 18:35:58,565][1045499] Updated weights for policy 0, policy_version 4089 (0.0007) -[2023-03-02 18:35:59,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12356.3, 300 sec: 12185.6). Total num frames: 4196352. Throughput: 0: 12346.7. Samples: 2535304. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:35:59,314][1045180] Avg episode reward: [(0, '18.036')] -[2023-03-02 18:35:59,365][1045499] Updated weights for policy 0, policy_version 4099 (0.0007) -[2023-03-02 18:36:00,192][1045499] Updated weights for policy 0, policy_version 4109 (0.0007) -[2023-03-02 18:36:01,055][1045499] Updated weights for policy 0, policy_version 4119 (0.0007) -[2023-03-02 18:36:01,888][1045499] Updated weights for policy 0, policy_version 4129 (0.0008) -[2023-03-02 18:36:02,708][1045499] Updated weights for policy 0, policy_version 4139 (0.0006) -[2023-03-02 18:36:03,538][1045499] Updated weights for policy 0, policy_version 4149 (0.0007) -[2023-03-02 18:36:04,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12356.3, 300 sec: 12188.0). Total num frames: 4257792. Throughput: 0: 12356.3. Samples: 2609214. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:04,314][1045180] Avg episode reward: [(0, '17.536')] -[2023-03-02 18:36:04,352][1045499] Updated weights for policy 0, policy_version 4159 (0.0007) -[2023-03-02 18:36:05,180][1045499] Updated weights for policy 0, policy_version 4169 (0.0006) -[2023-03-02 18:36:06,017][1045499] Updated weights for policy 0, policy_version 4179 (0.0006) -[2023-03-02 18:36:06,842][1045499] Updated weights for policy 0, policy_version 4189 (0.0007) -[2023-03-02 18:36:07,657][1045499] Updated weights for policy 0, policy_version 4199 (0.0007) -[2023-03-02 18:36:08,505][1045499] Updated weights for policy 0, policy_version 4209 (0.0007) -[2023-03-02 18:36:09,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12339.2, 300 sec: 12190.3). Total num frames: 4319232. Throughput: 0: 12367.5. Samples: 2683342. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:09,314][1045180] Avg episode reward: [(0, '12.739')] -[2023-03-02 18:36:09,355][1045499] Updated weights for policy 0, policy_version 4219 (0.0006) -[2023-03-02 18:36:10,169][1045499] Updated weights for policy 0, policy_version 4229 (0.0007) -[2023-03-02 18:36:11,020][1045499] Updated weights for policy 0, policy_version 4239 (0.0006) -[2023-03-02 18:36:11,825][1045499] Updated weights for policy 0, policy_version 4249 (0.0006) -[2023-03-02 18:36:12,648][1045499] Updated weights for policy 0, policy_version 4259 (0.0006) -[2023-03-02 18:36:13,487][1045499] Updated weights for policy 0, policy_version 4269 (0.0007) -[2023-03-02 18:36:14,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12339.2, 300 sec: 12192.4). Total num frames: 4380672. Throughput: 0: 12385.3. Samples: 2720559. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:36:14,314][1045180] Avg episode reward: [(0, '13.930')] -[2023-03-02 18:36:14,316][1045499] Updated weights for policy 0, policy_version 4279 (0.0007) -[2023-03-02 18:36:15,132][1045499] Updated weights for policy 0, policy_version 4289 (0.0007) -[2023-03-02 18:36:15,974][1045499] Updated weights for policy 0, policy_version 4299 (0.0008) -[2023-03-02 18:36:16,799][1045499] Updated weights for policy 0, policy_version 4309 (0.0007) -[2023-03-02 18:36:17,612][1045499] Updated weights for policy 0, policy_version 4319 (0.0007) -[2023-03-02 18:36:18,437][1045499] Updated weights for policy 0, policy_version 4329 (0.0007) -[2023-03-02 18:36:19,272][1045499] Updated weights for policy 0, policy_version 4339 (0.0007) -[2023-03-02 18:36:19,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12356.3, 300 sec: 12199.0). Total num frames: 4443136. Throughput: 0: 12386.8. Samples: 2794972. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:19,314][1045180] Avg episode reward: [(0, '16.766')] -[2023-03-02 18:36:19,324][1045448] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000004340_4444160.pth... -[2023-03-02 18:36:19,356][1045448] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000001599_1637376.pth -[2023-03-02 18:36:20,093][1045499] Updated weights for policy 0, policy_version 4349 (0.0006) -[2023-03-02 18:36:20,916][1045499] Updated weights for policy 0, policy_version 4359 (0.0007) -[2023-03-02 18:36:21,738][1045499] Updated weights for policy 0, policy_version 4369 (0.0007) -[2023-03-02 18:36:22,564][1045499] Updated weights for policy 0, policy_version 4379 (0.0006) -[2023-03-02 18:36:23,389][1045499] Updated weights for policy 0, policy_version 4389 (0.0007) -[2023-03-02 18:36:24,205][1045499] Updated weights for policy 0, policy_version 4399 (0.0006) -[2023-03-02 18:36:24,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12373.3, 300 sec: 12205.2). Total num frames: 4505600. Throughput: 0: 12385.2. Samples: 2869494. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:24,314][1045180] Avg episode reward: [(0, '13.664')] -[2023-03-02 18:36:25,019][1045499] Updated weights for policy 0, policy_version 4409 (0.0006) -[2023-03-02 18:36:25,879][1045499] Updated weights for policy 0, policy_version 4419 (0.0007) -[2023-03-02 18:36:26,699][1045499] Updated weights for policy 0, policy_version 4429 (0.0006) -[2023-03-02 18:36:27,519][1045499] Updated weights for policy 0, policy_version 4439 (0.0006) -[2023-03-02 18:36:28,368][1045499] Updated weights for policy 0, policy_version 4449 (0.0008) -[2023-03-02 18:36:29,208][1045499] Updated weights for policy 0, policy_version 4459 (0.0006) -[2023-03-02 18:36:29,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12390.4, 300 sec: 12206.9). Total num frames: 4567040. Throughput: 0: 12386.7. Samples: 2906347. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:29,314][1045180] Avg episode reward: [(0, '18.686')] -[2023-03-02 18:36:30,048][1045499] Updated weights for policy 0, policy_version 4469 (0.0008) -[2023-03-02 18:36:30,880][1045499] Updated weights for policy 0, policy_version 4479 (0.0006) -[2023-03-02 18:36:31,705][1045499] Updated weights for policy 0, policy_version 4489 (0.0007) -[2023-03-02 18:36:32,541][1045499] Updated weights for policy 0, policy_version 4499 (0.0006) -[2023-03-02 18:36:33,372][1045499] Updated weights for policy 0, policy_version 4509 (0.0006) -[2023-03-02 18:36:34,184][1045499] Updated weights for policy 0, policy_version 4519 (0.0006) -[2023-03-02 18:36:34,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12373.3, 300 sec: 12208.6). Total num frames: 4628480. Throughput: 0: 12381.2. Samples: 2980153. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:34,314][1045180] Avg episode reward: [(0, '15.073')] -[2023-03-02 18:36:35,023][1045499] Updated weights for policy 0, policy_version 4529 (0.0007) -[2023-03-02 18:36:35,833][1045499] Updated weights for policy 0, policy_version 4539 (0.0006) -[2023-03-02 18:36:36,685][1045499] Updated weights for policy 0, policy_version 4549 (0.0007) -[2023-03-02 18:36:37,513][1045499] Updated weights for policy 0, policy_version 4559 (0.0007) -[2023-03-02 18:36:38,352][1045499] Updated weights for policy 0, policy_version 4569 (0.0006) -[2023-03-02 18:36:39,180][1045499] Updated weights for policy 0, policy_version 4579 (0.0007) -[2023-03-02 18:36:39,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12356.4, 300 sec: 12210.2). Total num frames: 4689920. Throughput: 0: 12358.7. Samples: 3053944. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:36:39,314][1045180] Avg episode reward: [(0, '13.465')] -[2023-03-02 18:36:40,002][1045499] Updated weights for policy 0, policy_version 4589 (0.0007) -[2023-03-02 18:36:40,824][1045499] Updated weights for policy 0, policy_version 4599 (0.0006) -[2023-03-02 18:36:41,644][1045499] Updated weights for policy 0, policy_version 4609 (0.0008) -[2023-03-02 18:36:42,453][1045499] Updated weights for policy 0, policy_version 4619 (0.0007) -[2023-03-02 18:36:43,276][1045499] Updated weights for policy 0, policy_version 4629 (0.0007) -[2023-03-02 18:36:44,097][1045499] Updated weights for policy 0, policy_version 4639 (0.0007) -[2023-03-02 18:36:44,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12373.3, 300 sec: 12215.7). Total num frames: 4752384. Throughput: 0: 12361.6. Samples: 3091574. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:44,314][1045180] Avg episode reward: [(0, '9.541')] -[2023-03-02 18:36:44,941][1045499] Updated weights for policy 0, policy_version 4649 (0.0007) -[2023-03-02 18:36:45,799][1045499] Updated weights for policy 0, policy_version 4659 (0.0007) -[2023-03-02 18:36:46,610][1045499] Updated weights for policy 0, policy_version 4669 (0.0006) -[2023-03-02 18:36:47,448][1045499] Updated weights for policy 0, policy_version 4679 (0.0007) -[2023-03-02 18:36:48,264][1045499] Updated weights for policy 0, policy_version 4689 (0.0006) -[2023-03-02 18:36:49,105][1045499] Updated weights for policy 0, policy_version 4699 (0.0007) -[2023-03-02 18:36:49,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12373.3, 300 sec: 12217.1). Total num frames: 4813824. Throughput: 0: 12366.7. Samples: 3165717. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:36:49,314][1045180] Avg episode reward: [(0, '9.880')] -[2023-03-02 18:36:49,938][1045499] Updated weights for policy 0, policy_version 4709 (0.0006) -[2023-03-02 18:36:50,753][1045499] Updated weights for policy 0, policy_version 4719 (0.0007) -[2023-03-02 18:36:51,569][1045499] Updated weights for policy 0, policy_version 4729 (0.0006) -[2023-03-02 18:36:52,406][1045499] Updated weights for policy 0, policy_version 4739 (0.0007) -[2023-03-02 18:36:53,241][1045499] Updated weights for policy 0, policy_version 4749 (0.0007) -[2023-03-02 18:36:54,093][1045499] Updated weights for policy 0, policy_version 4759 (0.0007) -[2023-03-02 18:36:54,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12218.5). Total num frames: 4875264. Throughput: 0: 12359.1. Samples: 3239499. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:36:54,314][1045180] Avg episode reward: [(0, '8.232')] -[2023-03-02 18:36:54,920][1045499] Updated weights for policy 0, policy_version 4769 (0.0007) -[2023-03-02 18:36:55,726][1045499] Updated weights for policy 0, policy_version 4779 (0.0007) -[2023-03-02 18:36:56,553][1045499] Updated weights for policy 0, policy_version 4789 (0.0007) -[2023-03-02 18:36:57,386][1045499] Updated weights for policy 0, policy_version 4799 (0.0007) -[2023-03-02 18:36:58,194][1045499] Updated weights for policy 0, policy_version 4809 (0.0007) -[2023-03-02 18:36:58,988][1045499] Updated weights for policy 0, policy_version 4819 (0.0007) -[2023-03-02 18:36:59,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12356.3, 300 sec: 12223.5). Total num frames: 4937728. Throughput: 0: 12360.8. Samples: 3276795. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:36:59,314][1045180] Avg episode reward: [(0, '9.039')] -[2023-03-02 18:36:59,822][1045499] Updated weights for policy 0, policy_version 4829 (0.0007) -[2023-03-02 18:37:00,647][1045499] Updated weights for policy 0, policy_version 4839 (0.0007) -[2023-03-02 18:37:01,486][1045499] Updated weights for policy 0, policy_version 4849 (0.0007) -[2023-03-02 18:37:02,329][1045499] Updated weights for policy 0, policy_version 4859 (0.0006) -[2023-03-02 18:37:03,150][1045499] Updated weights for policy 0, policy_version 4869 (0.0006) -[2023-03-02 18:37:03,970][1045499] Updated weights for policy 0, policy_version 4879 (0.0007) -[2023-03-02 18:37:04,313][1045180] Fps is (10 sec: 12492.7, 60 sec: 12373.3, 300 sec: 12228.4). Total num frames: 5000192. Throughput: 0: 12370.0. Samples: 3351623. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:37:04,314][1045180] Avg episode reward: [(0, '7.845')] -[2023-03-02 18:37:04,798][1045499] Updated weights for policy 0, policy_version 4889 (0.0008) -[2023-03-02 18:37:05,628][1045499] Updated weights for policy 0, policy_version 4899 (0.0007) -[2023-03-02 18:37:06,449][1045499] Updated weights for policy 0, policy_version 4909 (0.0006) -[2023-03-02 18:37:07,274][1045499] Updated weights for policy 0, policy_version 4919 (0.0006) -[2023-03-02 18:37:08,110][1045499] Updated weights for policy 0, policy_version 4929 (0.0006) -[2023-03-02 18:37:08,928][1045499] Updated weights for policy 0, policy_version 4939 (0.0007) -[2023-03-02 18:37:09,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12229.5). Total num frames: 5061632. Throughput: 0: 12363.4. Samples: 3425849. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:37:09,314][1045180] Avg episode reward: [(0, '7.902')] -[2023-03-02 18:37:09,747][1045499] Updated weights for policy 0, policy_version 4949 (0.0006) -[2023-03-02 18:37:10,555][1045499] Updated weights for policy 0, policy_version 4959 (0.0007) -[2023-03-02 18:37:11,396][1045499] Updated weights for policy 0, policy_version 4969 (0.0007) -[2023-03-02 18:37:12,209][1045499] Updated weights for policy 0, policy_version 4979 (0.0006) -[2023-03-02 18:37:13,047][1045499] Updated weights for policy 0, policy_version 4989 (0.0006) -[2023-03-02 18:37:13,851][1045499] Updated weights for policy 0, policy_version 4999 (0.0007) -[2023-03-02 18:37:14,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12390.4, 300 sec: 12234.1). Total num frames: 5124096. Throughput: 0: 12377.8. Samples: 3463348. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:37:14,314][1045180] Avg episode reward: [(0, '6.443')] -[2023-03-02 18:37:14,657][1045499] Updated weights for policy 0, policy_version 5009 (0.0006) -[2023-03-02 18:37:15,501][1045499] Updated weights for policy 0, policy_version 5019 (0.0007) -[2023-03-02 18:37:16,315][1045499] Updated weights for policy 0, policy_version 5029 (0.0006) -[2023-03-02 18:37:17,133][1045499] Updated weights for policy 0, policy_version 5039 (0.0006) -[2023-03-02 18:37:17,969][1045499] Updated weights for policy 0, policy_version 5049 (0.0006) -[2023-03-02 18:37:18,784][1045499] Updated weights for policy 0, policy_version 5059 (0.0007) -[2023-03-02 18:37:19,313][1045180] Fps is (10 sec: 12492.9, 60 sec: 12390.4, 300 sec: 12238.6). Total num frames: 5186560. Throughput: 0: 12402.5. Samples: 3538266. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:37:19,314][1045180] Avg episode reward: [(0, '6.611')] -[2023-03-02 18:37:19,424][1045448] KL-divergence is very high: 3397.6538 -[2023-03-02 18:37:19,499][1045448] KL-divergence is very high: 173.7547 -[2023-03-02 18:37:19,606][1045499] Updated weights for policy 0, policy_version 5069 (0.0007) -[2023-03-02 18:37:20,425][1045499] Updated weights for policy 0, policy_version 5079 (0.0007) -[2023-03-02 18:37:21,257][1045499] Updated weights for policy 0, policy_version 5089 (0.0006) -[2023-03-02 18:37:22,065][1045499] Updated weights for policy 0, policy_version 5099 (0.0007) -[2023-03-02 18:37:22,893][1045499] Updated weights for policy 0, policy_version 5109 (0.0006) -[2023-03-02 18:37:23,733][1045499] Updated weights for policy 0, policy_version 5119 (0.0006) -[2023-03-02 18:37:24,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12239.4). Total num frames: 5248000. Throughput: 0: 12406.3. Samples: 3612229. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:37:24,314][1045180] Avg episode reward: [(0, '7.101')] -[2023-03-02 18:37:24,560][1045499] Updated weights for policy 0, policy_version 5129 (0.0007) -[2023-03-02 18:37:25,391][1045499] Updated weights for policy 0, policy_version 5139 (0.0007) -[2023-03-02 18:37:26,239][1045499] Updated weights for policy 0, policy_version 5149 (0.0007) -[2023-03-02 18:37:27,061][1045499] Updated weights for policy 0, policy_version 5159 (0.0007) -[2023-03-02 18:37:27,904][1045499] Updated weights for policy 0, policy_version 5169 (0.0008) -[2023-03-02 18:37:28,715][1045499] Updated weights for policy 0, policy_version 5179 (0.0006) -[2023-03-02 18:37:29,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12390.4, 300 sec: 12347.0). Total num frames: 5310464. Throughput: 0: 12395.8. Samples: 3649383. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:37:29,314][1045180] Avg episode reward: [(0, '6.557')] -[2023-03-02 18:37:29,539][1045499] Updated weights for policy 0, policy_version 5189 (0.0006) -[2023-03-02 18:37:30,391][1045499] Updated weights for policy 0, policy_version 5199 (0.0006) -[2023-03-02 18:37:31,217][1045499] Updated weights for policy 0, policy_version 5209 (0.0007) -[2023-03-02 18:37:32,039][1045499] Updated weights for policy 0, policy_version 5219 (0.0006) -[2023-03-02 18:37:32,870][1045499] Updated weights for policy 0, policy_version 5229 (0.0007) -[2023-03-02 18:37:33,703][1045499] Updated weights for policy 0, policy_version 5239 (0.0007) -[2023-03-02 18:37:34,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12390.4, 300 sec: 12347.0). Total num frames: 5371904. Throughput: 0: 12392.0. Samples: 3723358. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:37:34,314][1045180] Avg episode reward: [(0, '7.085')] -[2023-03-02 18:37:34,508][1045499] Updated weights for policy 0, policy_version 5249 (0.0008) -[2023-03-02 18:37:35,308][1045499] Updated weights for policy 0, policy_version 5259 (0.0006) -[2023-03-02 18:37:36,134][1045499] Updated weights for policy 0, policy_version 5269 (0.0006) -[2023-03-02 18:37:36,952][1045499] Updated weights for policy 0, policy_version 5279 (0.0007) -[2023-03-02 18:37:37,713][1045448] KL-divergence is very high: 644.2097 -[2023-03-02 18:37:37,795][1045499] Updated weights for policy 0, policy_version 5289 (0.0007) -[2023-03-02 18:37:38,596][1045499] Updated weights for policy 0, policy_version 5299 (0.0007) -[2023-03-02 18:37:39,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12407.4, 300 sec: 12350.5). Total num frames: 5434368. Throughput: 0: 12417.4. Samples: 3798283. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:37:39,314][1045180] Avg episode reward: [(0, '7.545')] -[2023-03-02 18:37:39,439][1045499] Updated weights for policy 0, policy_version 5309 (0.0008) -[2023-03-02 18:37:40,272][1045499] Updated weights for policy 0, policy_version 5319 (0.0007) -[2023-03-02 18:37:41,120][1045499] Updated weights for policy 0, policy_version 5329 (0.0007) -[2023-03-02 18:37:41,930][1045499] Updated weights for policy 0, policy_version 5339 (0.0007) -[2023-03-02 18:37:42,769][1045499] Updated weights for policy 0, policy_version 5349 (0.0008) -[2023-03-02 18:37:43,606][1045499] Updated weights for policy 0, policy_version 5359 (0.0007) -[2023-03-02 18:37:44,313][1045180] Fps is (10 sec: 12390.6, 60 sec: 12390.4, 300 sec: 12350.5). Total num frames: 5495808. Throughput: 0: 12411.6. Samples: 3835315. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:37:44,314][1045180] Avg episode reward: [(0, '7.400')] -[2023-03-02 18:37:44,431][1045499] Updated weights for policy 0, policy_version 5369 (0.0007) -[2023-03-02 18:37:45,240][1045499] Updated weights for policy 0, policy_version 5379 (0.0006) -[2023-03-02 18:37:46,062][1045499] Updated weights for policy 0, policy_version 5389 (0.0006) -[2023-03-02 18:37:46,888][1045499] Updated weights for policy 0, policy_version 5399 (0.0007) -[2023-03-02 18:37:47,714][1045499] Updated weights for policy 0, policy_version 5409 (0.0006) -[2023-03-02 18:37:48,554][1045499] Updated weights for policy 0, policy_version 5419 (0.0006) -[2023-03-02 18:37:49,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12390.4, 300 sec: 12350.5). Total num frames: 5557248. Throughput: 0: 12401.7. Samples: 3909699. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:37:49,314][1045180] Avg episode reward: [(0, '7.202')] -[2023-03-02 18:37:49,413][1045499] Updated weights for policy 0, policy_version 5429 (0.0006) -[2023-03-02 18:37:50,236][1045499] Updated weights for policy 0, policy_version 5439 (0.0007) -[2023-03-02 18:37:51,066][1045499] Updated weights for policy 0, policy_version 5449 (0.0007) -[2023-03-02 18:37:51,884][1045499] Updated weights for policy 0, policy_version 5459 (0.0006) -[2023-03-02 18:37:52,705][1045499] Updated weights for policy 0, policy_version 5469 (0.0007) -[2023-03-02 18:37:53,561][1045499] Updated weights for policy 0, policy_version 5479 (0.0007) -[2023-03-02 18:37:54,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12407.5, 300 sec: 12354.0). Total num frames: 5619712. Throughput: 0: 12390.5. Samples: 3983418. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:37:54,314][1045180] Avg episode reward: [(0, '7.069')] -[2023-03-02 18:37:54,377][1045499] Updated weights for policy 0, policy_version 5489 (0.0007) -[2023-03-02 18:37:55,200][1045499] Updated weights for policy 0, policy_version 5499 (0.0007) -[2023-03-02 18:37:56,023][1045499] Updated weights for policy 0, policy_version 5509 (0.0007) -[2023-03-02 18:37:56,812][1045499] Updated weights for policy 0, policy_version 5519 (0.0007) -[2023-03-02 18:37:57,639][1045499] Updated weights for policy 0, policy_version 5529 (0.0007) -[2023-03-02 18:37:58,463][1045499] Updated weights for policy 0, policy_version 5539 (0.0006) -[2023-03-02 18:37:59,291][1045499] Updated weights for policy 0, policy_version 5549 (0.0007) -[2023-03-02 18:37:59,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12407.5, 300 sec: 12360.9). Total num frames: 5682176. Throughput: 0: 12396.1. Samples: 4021174. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:37:59,314][1045180] Avg episode reward: [(0, '7.178')] -[2023-03-02 18:38:00,132][1045499] Updated weights for policy 0, policy_version 5559 (0.0007) -[2023-03-02 18:38:00,985][1045499] Updated weights for policy 0, policy_version 5569 (0.0006) -[2023-03-02 18:38:01,825][1045499] Updated weights for policy 0, policy_version 5579 (0.0006) -[2023-03-02 18:38:02,645][1045499] Updated weights for policy 0, policy_version 5589 (0.0007) -[2023-03-02 18:38:03,476][1045499] Updated weights for policy 0, policy_version 5599 (0.0006) -[2023-03-02 18:38:04,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12373.3, 300 sec: 12357.4). Total num frames: 5742592. Throughput: 0: 12368.9. Samples: 4094868. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:04,314][1045180] Avg episode reward: [(0, '6.660')] -[2023-03-02 18:38:04,316][1045499] Updated weights for policy 0, policy_version 5609 (0.0007) -[2023-03-02 18:38:05,125][1045499] Updated weights for policy 0, policy_version 5619 (0.0007) -[2023-03-02 18:38:05,980][1045499] Updated weights for policy 0, policy_version 5629 (0.0009) -[2023-03-02 18:38:06,816][1045499] Updated weights for policy 0, policy_version 5639 (0.0006) -[2023-03-02 18:38:07,629][1045499] Updated weights for policy 0, policy_version 5649 (0.0006) -[2023-03-02 18:38:08,448][1045499] Updated weights for policy 0, policy_version 5659 (0.0007) -[2023-03-02 18:38:09,282][1045499] Updated weights for policy 0, policy_version 5669 (0.0008) -[2023-03-02 18:38:09,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12390.4, 300 sec: 12360.9). Total num frames: 5805056. Throughput: 0: 12370.9. Samples: 4168918. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:38:09,314][1045180] Avg episode reward: [(0, '8.186')] -[2023-03-02 18:38:10,105][1045499] Updated weights for policy 0, policy_version 5679 (0.0007) -[2023-03-02 18:38:10,917][1045499] Updated weights for policy 0, policy_version 5689 (0.0006) -[2023-03-02 18:38:11,736][1045499] Updated weights for policy 0, policy_version 5699 (0.0007) -[2023-03-02 18:38:12,572][1045499] Updated weights for policy 0, policy_version 5709 (0.0006) -[2023-03-02 18:38:13,402][1045499] Updated weights for policy 0, policy_version 5719 (0.0006) -[2023-03-02 18:38:14,240][1045499] Updated weights for policy 0, policy_version 5729 (0.0006) -[2023-03-02 18:38:14,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12373.3, 300 sec: 12360.9). Total num frames: 5866496. Throughput: 0: 12373.6. Samples: 4206195. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:14,314][1045180] Avg episode reward: [(0, '7.735')] -[2023-03-02 18:38:15,074][1045499] Updated weights for policy 0, policy_version 5739 (0.0007) -[2023-03-02 18:38:15,922][1045499] Updated weights for policy 0, policy_version 5749 (0.0006) -[2023-03-02 18:38:16,749][1045499] Updated weights for policy 0, policy_version 5759 (0.0007) -[2023-03-02 18:38:17,571][1045499] Updated weights for policy 0, policy_version 5769 (0.0006) -[2023-03-02 18:38:18,389][1045499] Updated weights for policy 0, policy_version 5779 (0.0006) -[2023-03-02 18:38:19,220][1045499] Updated weights for policy 0, policy_version 5789 (0.0006) -[2023-03-02 18:38:19,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12373.3, 300 sec: 12360.9). Total num frames: 5928960. Throughput: 0: 12373.8. Samples: 4280180. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:38:19,314][1045180] Avg episode reward: [(0, '6.788')] -[2023-03-02 18:38:19,317][1045448] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000005790_5928960.pth... -[2023-03-02 18:38:19,352][1045448] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000002894_2963456.pth -[2023-03-02 18:38:20,052][1045499] Updated weights for policy 0, policy_version 5799 (0.0008) -[2023-03-02 18:38:20,873][1045499] Updated weights for policy 0, policy_version 5809 (0.0007) -[2023-03-02 18:38:21,725][1045499] Updated weights for policy 0, policy_version 5819 (0.0007) -[2023-03-02 18:38:22,556][1045499] Updated weights for policy 0, policy_version 5829 (0.0006) -[2023-03-02 18:38:23,373][1045499] Updated weights for policy 0, policy_version 5839 (0.0006) -[2023-03-02 18:38:24,200][1045499] Updated weights for policy 0, policy_version 5849 (0.0007) -[2023-03-02 18:38:24,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12373.3, 300 sec: 12360.9). Total num frames: 5990400. Throughput: 0: 12359.4. Samples: 4354456. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:38:24,314][1045180] Avg episode reward: [(0, '6.880')] -[2023-03-02 18:38:25,028][1045499] Updated weights for policy 0, policy_version 5859 (0.0006) -[2023-03-02 18:38:25,846][1045499] Updated weights for policy 0, policy_version 5869 (0.0007) -[2023-03-02 18:38:26,669][1045499] Updated weights for policy 0, policy_version 5879 (0.0007) -[2023-03-02 18:38:27,482][1045499] Updated weights for policy 0, policy_version 5889 (0.0006) -[2023-03-02 18:38:28,320][1045499] Updated weights for policy 0, policy_version 5899 (0.0007) -[2023-03-02 18:38:29,157][1045499] Updated weights for policy 0, policy_version 5909 (0.0006) -[2023-03-02 18:38:29,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12373.3, 300 sec: 12364.4). Total num frames: 6052864. Throughput: 0: 12366.8. Samples: 4391822. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:38:29,314][1045180] Avg episode reward: [(0, '6.661')] -[2023-03-02 18:38:29,977][1045499] Updated weights for policy 0, policy_version 5919 (0.0007) -[2023-03-02 18:38:30,782][1045499] Updated weights for policy 0, policy_version 5929 (0.0007) -[2023-03-02 18:38:31,613][1045499] Updated weights for policy 0, policy_version 5939 (0.0007) -[2023-03-02 18:38:32,448][1045499] Updated weights for policy 0, policy_version 5949 (0.0007) -[2023-03-02 18:38:33,271][1045499] Updated weights for policy 0, policy_version 5959 (0.0008) -[2023-03-02 18:38:34,092][1045499] Updated weights for policy 0, policy_version 5969 (0.0007) -[2023-03-02 18:38:34,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12364.4). Total num frames: 6114304. Throughput: 0: 12360.3. Samples: 4465912. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:34,314][1045180] Avg episode reward: [(0, '7.973')] -[2023-03-02 18:38:34,923][1045499] Updated weights for policy 0, policy_version 5979 (0.0007) -[2023-03-02 18:38:35,763][1045499] Updated weights for policy 0, policy_version 5989 (0.0006) -[2023-03-02 18:38:36,624][1045499] Updated weights for policy 0, policy_version 5999 (0.0006) -[2023-03-02 18:38:37,431][1045499] Updated weights for policy 0, policy_version 6009 (0.0006) -[2023-03-02 18:38:38,258][1045499] Updated weights for policy 0, policy_version 6019 (0.0007) -[2023-03-02 18:38:39,111][1045499] Updated weights for policy 0, policy_version 6029 (0.0006) -[2023-03-02 18:38:39,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12357.4). Total num frames: 6175744. Throughput: 0: 12363.4. Samples: 4539770. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:39,314][1045180] Avg episode reward: [(0, '7.047')] -[2023-03-02 18:38:39,958][1045499] Updated weights for policy 0, policy_version 6039 (0.0007) -[2023-03-02 18:38:40,786][1045499] Updated weights for policy 0, policy_version 6049 (0.0007) -[2023-03-02 18:38:41,593][1045499] Updated weights for policy 0, policy_version 6059 (0.0007) -[2023-03-02 18:38:42,421][1045499] Updated weights for policy 0, policy_version 6069 (0.0006) -[2023-03-02 18:38:43,254][1045499] Updated weights for policy 0, policy_version 6079 (0.0007) -[2023-03-02 18:38:44,101][1045499] Updated weights for policy 0, policy_version 6089 (0.0007) -[2023-03-02 18:38:44,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12356.2, 300 sec: 12357.4). Total num frames: 6237184. Throughput: 0: 12348.1. Samples: 4576838. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:38:44,314][1045180] Avg episode reward: [(0, '7.718')] -[2023-03-02 18:38:44,942][1045499] Updated weights for policy 0, policy_version 6099 (0.0007) -[2023-03-02 18:38:45,769][1045499] Updated weights for policy 0, policy_version 6109 (0.0007) -[2023-03-02 18:38:46,595][1045499] Updated weights for policy 0, policy_version 6119 (0.0007) -[2023-03-02 18:38:47,437][1045499] Updated weights for policy 0, policy_version 6129 (0.0007) -[2023-03-02 18:38:48,268][1045499] Updated weights for policy 0, policy_version 6139 (0.0006) -[2023-03-02 18:38:49,066][1045499] Updated weights for policy 0, policy_version 6149 (0.0006) -[2023-03-02 18:38:49,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12357.4). Total num frames: 6298624. Throughput: 0: 12348.9. Samples: 4650568. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:49,314][1045180] Avg episode reward: [(0, '7.382')] -[2023-03-02 18:38:49,922][1045499] Updated weights for policy 0, policy_version 6159 (0.0007) -[2023-03-02 18:38:50,746][1045499] Updated weights for policy 0, policy_version 6169 (0.0006) -[2023-03-02 18:38:51,578][1045499] Updated weights for policy 0, policy_version 6179 (0.0007) -[2023-03-02 18:38:52,424][1045499] Updated weights for policy 0, policy_version 6189 (0.0007) -[2023-03-02 18:38:53,272][1045499] Updated weights for policy 0, policy_version 6199 (0.0008) -[2023-03-02 18:38:54,110][1045499] Updated weights for policy 0, policy_version 6209 (0.0006) -[2023-03-02 18:38:54,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12339.2, 300 sec: 12354.0). Total num frames: 6360064. Throughput: 0: 12337.4. Samples: 4724101. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:38:54,314][1045180] Avg episode reward: [(0, '7.240')] -[2023-03-02 18:38:54,924][1045499] Updated weights for policy 0, policy_version 6219 (0.0006) -[2023-03-02 18:38:55,755][1045499] Updated weights for policy 0, policy_version 6229 (0.0006) -[2023-03-02 18:38:56,587][1045499] Updated weights for policy 0, policy_version 6239 (0.0006) -[2023-03-02 18:38:57,413][1045499] Updated weights for policy 0, policy_version 6249 (0.0007) -[2023-03-02 18:38:58,241][1045499] Updated weights for policy 0, policy_version 6259 (0.0006) -[2023-03-02 18:38:59,044][1045499] Updated weights for policy 0, policy_version 6269 (0.0006) -[2023-03-02 18:38:59,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12339.2, 300 sec: 12354.0). Total num frames: 6422528. Throughput: 0: 12333.6. Samples: 4761209. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:38:59,314][1045180] Avg episode reward: [(0, '7.759')] -[2023-03-02 18:38:59,868][1045499] Updated weights for policy 0, policy_version 6279 (0.0007) -[2023-03-02 18:39:00,674][1045499] Updated weights for policy 0, policy_version 6289 (0.0007) -[2023-03-02 18:39:01,510][1045499] Updated weights for policy 0, policy_version 6299 (0.0007) -[2023-03-02 18:39:02,336][1045499] Updated weights for policy 0, policy_version 6309 (0.0007) -[2023-03-02 18:39:03,172][1045499] Updated weights for policy 0, policy_version 6319 (0.0008) -[2023-03-02 18:39:03,983][1045499] Updated weights for policy 0, policy_version 6329 (0.0007) -[2023-03-02 18:39:04,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12373.4, 300 sec: 12360.9). Total num frames: 6484992. Throughput: 0: 12354.6. Samples: 4836137. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:04,314][1045180] Avg episode reward: [(0, '6.903')] -[2023-03-02 18:39:04,803][1045499] Updated weights for policy 0, policy_version 6339 (0.0006) -[2023-03-02 18:39:05,616][1045499] Updated weights for policy 0, policy_version 6349 (0.0007) -[2023-03-02 18:39:06,437][1045499] Updated weights for policy 0, policy_version 6359 (0.0006) -[2023-03-02 18:39:07,280][1045499] Updated weights for policy 0, policy_version 6369 (0.0007) -[2023-03-02 18:39:08,092][1045499] Updated weights for policy 0, policy_version 6379 (0.0007) -[2023-03-02 18:39:08,918][1045499] Updated weights for policy 0, policy_version 6389 (0.0007) -[2023-03-02 18:39:09,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12356.2, 300 sec: 12357.4). Total num frames: 6546432. Throughput: 0: 12360.0. Samples: 4910657. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:09,314][1045180] Avg episode reward: [(0, '7.851')] -[2023-03-02 18:39:09,729][1045499] Updated weights for policy 0, policy_version 6399 (0.0007) -[2023-03-02 18:39:10,591][1045499] Updated weights for policy 0, policy_version 6409 (0.0007) -[2023-03-02 18:39:11,417][1045499] Updated weights for policy 0, policy_version 6419 (0.0007) -[2023-03-02 18:39:12,256][1045499] Updated weights for policy 0, policy_version 6429 (0.0006) -[2023-03-02 18:39:13,106][1045499] Updated weights for policy 0, policy_version 6439 (0.0007) -[2023-03-02 18:39:13,925][1045499] Updated weights for policy 0, policy_version 6449 (0.0006) -[2023-03-02 18:39:14,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12357.4). Total num frames: 6607872. Throughput: 0: 12350.9. Samples: 4947614. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0) -[2023-03-02 18:39:14,314][1045180] Avg episode reward: [(0, '7.440')] -[2023-03-02 18:39:14,736][1045499] Updated weights for policy 0, policy_version 6459 (0.0007) -[2023-03-02 18:39:15,563][1045499] Updated weights for policy 0, policy_version 6469 (0.0006) -[2023-03-02 18:39:16,386][1045499] Updated weights for policy 0, policy_version 6479 (0.0006) -[2023-03-02 18:39:17,213][1045499] Updated weights for policy 0, policy_version 6489 (0.0006) -[2023-03-02 18:39:18,031][1045499] Updated weights for policy 0, policy_version 6499 (0.0006) -[2023-03-02 18:39:18,843][1045499] Updated weights for policy 0, policy_version 6509 (0.0006) -[2023-03-02 18:39:19,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12356.3, 300 sec: 12360.9). Total num frames: 6670336. Throughput: 0: 12355.5. Samples: 5021908. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:19,314][1045180] Avg episode reward: [(0, '7.807')] -[2023-03-02 18:39:19,658][1045499] Updated weights for policy 0, policy_version 6519 (0.0007) -[2023-03-02 18:39:20,481][1045499] Updated weights for policy 0, policy_version 6529 (0.0006) -[2023-03-02 18:39:21,332][1045499] Updated weights for policy 0, policy_version 6539 (0.0006) -[2023-03-02 18:39:22,144][1045499] Updated weights for policy 0, policy_version 6549 (0.0007) -[2023-03-02 18:39:22,945][1045499] Updated weights for policy 0, policy_version 6559 (0.0006) -[2023-03-02 18:39:23,783][1045499] Updated weights for policy 0, policy_version 6569 (0.0006) -[2023-03-02 18:39:24,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12373.3, 300 sec: 12364.4). Total num frames: 6732800. Throughput: 0: 12382.7. Samples: 5096993. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0) -[2023-03-02 18:39:24,314][1045180] Avg episode reward: [(0, '8.402')] -[2023-03-02 18:39:24,581][1045499] Updated weights for policy 0, policy_version 6579 (0.0007) -[2023-03-02 18:39:25,420][1045499] Updated weights for policy 0, policy_version 6589 (0.0007) -[2023-03-02 18:39:26,288][1045499] Updated weights for policy 0, policy_version 6599 (0.0007) -[2023-03-02 18:39:27,091][1045499] Updated weights for policy 0, policy_version 6609 (0.0007) -[2023-03-02 18:39:27,927][1045499] Updated weights for policy 0, policy_version 6619 (0.0007) -[2023-03-02 18:39:28,748][1045499] Updated weights for policy 0, policy_version 6629 (0.0007) -[2023-03-02 18:39:29,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12356.2, 300 sec: 12364.4). Total num frames: 6794240. Throughput: 0: 12375.7. Samples: 5133742. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:39:29,314][1045180] Avg episode reward: [(0, '8.741')] -[2023-03-02 18:39:29,604][1045499] Updated weights for policy 0, policy_version 6639 (0.0006) -[2023-03-02 18:39:30,422][1045499] Updated weights for policy 0, policy_version 6649 (0.0007) -[2023-03-02 18:39:31,236][1045499] Updated weights for policy 0, policy_version 6659 (0.0007) -[2023-03-02 18:39:32,089][1045499] Updated weights for policy 0, policy_version 6669 (0.0007) -[2023-03-02 18:39:32,908][1045499] Updated weights for policy 0, policy_version 6679 (0.0007) -[2023-03-02 18:39:33,712][1045499] Updated weights for policy 0, policy_version 6689 (0.0006) -[2023-03-02 18:39:34,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12360.9). Total num frames: 6855680. Throughput: 0: 12383.7. Samples: 5207834. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:39:34,314][1045180] Avg episode reward: [(0, '8.348')] -[2023-03-02 18:39:34,554][1045499] Updated weights for policy 0, policy_version 6699 (0.0006) -[2023-03-02 18:39:35,354][1045499] Updated weights for policy 0, policy_version 6709 (0.0006) -[2023-03-02 18:39:36,206][1045499] Updated weights for policy 0, policy_version 6719 (0.0007) -[2023-03-02 18:39:37,052][1045499] Updated weights for policy 0, policy_version 6729 (0.0007) -[2023-03-02 18:39:37,883][1045499] Updated weights for policy 0, policy_version 6739 (0.0006) -[2023-03-02 18:39:38,722][1045499] Updated weights for policy 0, policy_version 6749 (0.0007) -[2023-03-02 18:39:39,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12360.9). Total num frames: 6917120. Throughput: 0: 12386.1. Samples: 5281475. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:39,314][1045180] Avg episode reward: [(0, '7.601')] -[2023-03-02 18:39:39,573][1045499] Updated weights for policy 0, policy_version 6759 (0.0006) -[2023-03-02 18:39:40,409][1045499] Updated weights for policy 0, policy_version 6769 (0.0008) -[2023-03-02 18:39:41,243][1045499] Updated weights for policy 0, policy_version 6779 (0.0007) -[2023-03-02 18:39:42,062][1045499] Updated weights for policy 0, policy_version 6789 (0.0007) -[2023-03-02 18:39:42,895][1045499] Updated weights for policy 0, policy_version 6799 (0.0006) -[2023-03-02 18:39:43,724][1045499] Updated weights for policy 0, policy_version 6809 (0.0006) -[2023-03-02 18:39:44,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12373.3, 300 sec: 12364.4). Total num frames: 6979584. Throughput: 0: 12380.0. Samples: 5318310. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:44,314][1045180] Avg episode reward: [(0, '8.140')] -[2023-03-02 18:39:44,572][1045499] Updated weights for policy 0, policy_version 6819 (0.0007) -[2023-03-02 18:39:45,392][1045499] Updated weights for policy 0, policy_version 6829 (0.0006) -[2023-03-02 18:39:46,206][1045499] Updated weights for policy 0, policy_version 6839 (0.0007) -[2023-03-02 18:39:47,064][1045499] Updated weights for policy 0, policy_version 6849 (0.0006) -[2023-03-02 18:39:47,859][1045499] Updated weights for policy 0, policy_version 6859 (0.0006) -[2023-03-02 18:39:48,718][1045499] Updated weights for policy 0, policy_version 6869 (0.0006) -[2023-03-02 18:39:49,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12373.3, 300 sec: 12364.4). Total num frames: 7041024. Throughput: 0: 12366.6. Samples: 5392634. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:39:49,314][1045180] Avg episode reward: [(0, '8.316')] -[2023-03-02 18:39:49,543][1045499] Updated weights for policy 0, policy_version 6879 (0.0006) -[2023-03-02 18:39:50,350][1045499] Updated weights for policy 0, policy_version 6889 (0.0006) -[2023-03-02 18:39:51,182][1045499] Updated weights for policy 0, policy_version 6899 (0.0007) -[2023-03-02 18:39:52,016][1045499] Updated weights for policy 0, policy_version 6909 (0.0008) -[2023-03-02 18:39:52,835][1045499] Updated weights for policy 0, policy_version 6919 (0.0007) -[2023-03-02 18:39:53,647][1045499] Updated weights for policy 0, policy_version 6929 (0.0007) -[2023-03-02 18:39:54,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12390.4, 300 sec: 12367.8). Total num frames: 7103488. Throughput: 0: 12359.8. Samples: 5466845. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:39:54,313][1045180] Avg episode reward: [(0, '8.191')] -[2023-03-02 18:39:54,489][1045499] Updated weights for policy 0, policy_version 6939 (0.0006) -[2023-03-02 18:39:55,310][1045499] Updated weights for policy 0, policy_version 6949 (0.0007) -[2023-03-02 18:39:56,148][1045499] Updated weights for policy 0, policy_version 6959 (0.0007) -[2023-03-02 18:39:57,002][1045499] Updated weights for policy 0, policy_version 6969 (0.0007) -[2023-03-02 18:39:57,819][1045499] Updated weights for policy 0, policy_version 6979 (0.0007) -[2023-03-02 18:39:58,629][1045499] Updated weights for policy 0, policy_version 6989 (0.0007) -[2023-03-02 18:39:59,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12367.8). Total num frames: 7164928. Throughput: 0: 12353.9. Samples: 5503541. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:39:59,314][1045180] Avg episode reward: [(0, '7.433')] -[2023-03-02 18:39:59,444][1045499] Updated weights for policy 0, policy_version 6999 (0.0007) -[2023-03-02 18:40:00,278][1045499] Updated weights for policy 0, policy_version 7009 (0.0007) -[2023-03-02 18:40:01,101][1045499] Updated weights for policy 0, policy_version 7019 (0.0006) -[2023-03-02 18:40:01,945][1045499] Updated weights for policy 0, policy_version 7029 (0.0007) -[2023-03-02 18:40:02,761][1045499] Updated weights for policy 0, policy_version 7039 (0.0006) -[2023-03-02 18:40:03,628][1045499] Updated weights for policy 0, policy_version 7049 (0.0007) -[2023-03-02 18:40:04,313][1045180] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12364.4). Total num frames: 7226368. Throughput: 0: 12357.6. Samples: 5578000. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:40:04,314][1045180] Avg episode reward: [(0, '19.562')] -[2023-03-02 18:40:04,460][1045499] Updated weights for policy 0, policy_version 7059 (0.0008) -[2023-03-02 18:40:05,296][1045499] Updated weights for policy 0, policy_version 7069 (0.0006) -[2023-03-02 18:40:06,124][1045499] Updated weights for policy 0, policy_version 7079 (0.0007) -[2023-03-02 18:40:06,958][1045499] Updated weights for policy 0, policy_version 7089 (0.0007) -[2023-03-02 18:40:07,821][1045499] Updated weights for policy 0, policy_version 7099 (0.0008) -[2023-03-02 18:40:08,635][1045499] Updated weights for policy 0, policy_version 7109 (0.0007) -[2023-03-02 18:40:09,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12364.4). Total num frames: 7287808. Throughput: 0: 12328.9. Samples: 5651795. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:40:09,314][1045180] Avg episode reward: [(0, '7.684')] -[2023-03-02 18:40:09,438][1045499] Updated weights for policy 0, policy_version 7119 (0.0006) -[2023-03-02 18:40:10,261][1045499] Updated weights for policy 0, policy_version 7129 (0.0006) -[2023-03-02 18:40:11,074][1045499] Updated weights for policy 0, policy_version 7139 (0.0007) -[2023-03-02 18:40:11,893][1045499] Updated weights for policy 0, policy_version 7149 (0.0007) -[2023-03-02 18:40:12,712][1045499] Updated weights for policy 0, policy_version 7159 (0.0007) -[2023-03-02 18:40:13,529][1045499] Updated weights for policy 0, policy_version 7169 (0.0006) -[2023-03-02 18:40:14,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12373.3, 300 sec: 12367.8). Total num frames: 7350272. Throughput: 0: 12348.8. Samples: 5689438. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:40:14,314][1045180] Avg episode reward: [(0, '7.718')] -[2023-03-02 18:40:14,365][1045499] Updated weights for policy 0, policy_version 7179 (0.0006) -[2023-03-02 18:40:15,197][1045499] Updated weights for policy 0, policy_version 7189 (0.0006) -[2023-03-02 18:40:16,018][1045499] Updated weights for policy 0, policy_version 7199 (0.0006) -[2023-03-02 18:40:16,851][1045499] Updated weights for policy 0, policy_version 7209 (0.0006) -[2023-03-02 18:40:17,665][1045499] Updated weights for policy 0, policy_version 7219 (0.0006) -[2023-03-02 18:40:18,520][1045499] Updated weights for policy 0, policy_version 7229 (0.0007) -[2023-03-02 18:40:19,313][1045180] Fps is (10 sec: 12390.5, 60 sec: 12356.3, 300 sec: 12367.8). Total num frames: 7411712. Throughput: 0: 12348.9. Samples: 5763534. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:19,314][1045180] Avg episode reward: [(0, '6.800')] -[2023-03-02 18:40:19,317][1045448] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000007238_7411712.pth... -[2023-03-02 18:40:19,351][1045448] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000004340_4444160.pth -[2023-03-02 18:40:19,376][1045499] Updated weights for policy 0, policy_version 7239 (0.0007) -[2023-03-02 18:40:20,176][1045499] Updated weights for policy 0, policy_version 7249 (0.0007) -[2023-03-02 18:40:21,011][1045499] Updated weights for policy 0, policy_version 7259 (0.0006) -[2023-03-02 18:40:21,824][1045499] Updated weights for policy 0, policy_version 7269 (0.0007) -[2023-03-02 18:40:22,637][1045499] Updated weights for policy 0, policy_version 7279 (0.0006) -[2023-03-02 18:40:23,475][1045499] Updated weights for policy 0, policy_version 7289 (0.0007) -[2023-03-02 18:40:24,280][1045499] Updated weights for policy 0, policy_version 7299 (0.0006) -[2023-03-02 18:40:24,313][1045180] Fps is (10 sec: 12390.3, 60 sec: 12356.3, 300 sec: 12374.8). Total num frames: 7474176. Throughput: 0: 12367.8. Samples: 5838027. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:24,314][1045180] Avg episode reward: [(0, '7.901')] -[2023-03-02 18:40:25,112][1045499] Updated weights for policy 0, policy_version 7309 (0.0007) -[2023-03-02 18:40:25,927][1045499] Updated weights for policy 0, policy_version 7319 (0.0006) -[2023-03-02 18:40:26,750][1045499] Updated weights for policy 0, policy_version 7329 (0.0007) -[2023-03-02 18:40:27,579][1045499] Updated weights for policy 0, policy_version 7339 (0.0007) -[2023-03-02 18:40:28,428][1045499] Updated weights for policy 0, policy_version 7349 (0.0006) -[2023-03-02 18:40:29,234][1045499] Updated weights for policy 0, policy_version 7359 (0.0008) -[2023-03-02 18:40:29,313][1045180] Fps is (10 sec: 12492.8, 60 sec: 12373.3, 300 sec: 12374.8). Total num frames: 7536640. Throughput: 0: 12377.7. Samples: 5875306. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:29,314][1045180] Avg episode reward: [(0, '7.309')] -[2023-03-02 18:40:30,051][1045499] Updated weights for policy 0, policy_version 7369 (0.0006) -[2023-03-02 18:40:30,896][1045499] Updated weights for policy 0, policy_version 7379 (0.0006) -[2023-03-02 18:40:31,749][1045499] Updated weights for policy 0, policy_version 7389 (0.0006) -[2023-03-02 18:40:32,611][1045499] Updated weights for policy 0, policy_version 7399 (0.0007) -[2023-03-02 18:40:33,443][1045499] Updated weights for policy 0, policy_version 7409 (0.0006) -[2023-03-02 18:40:34,278][1045499] Updated weights for policy 0, policy_version 7419 (0.0006) -[2023-03-02 18:40:34,313][1045180] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12367.9). Total num frames: 7597056. Throughput: 0: 12356.7. Samples: 5948685. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:34,314][1045180] Avg episode reward: [(0, '9.203')] -[2023-03-02 18:40:35,131][1045499] Updated weights for policy 0, policy_version 7429 (0.0007) -[2023-03-02 18:40:35,950][1045499] Updated weights for policy 0, policy_version 7439 (0.0007) -[2023-03-02 18:40:36,799][1045499] Updated weights for policy 0, policy_version 7449 (0.0007) -[2023-03-02 18:40:37,620][1045499] Updated weights for policy 0, policy_version 7459 (0.0007) -[2023-03-02 18:40:38,458][1045499] Updated weights for policy 0, policy_version 7469 (0.0007) -[2023-03-02 18:40:39,280][1045499] Updated weights for policy 0, policy_version 7479 (0.0006) -[2023-03-02 18:40:39,313][1045180] Fps is (10 sec: 12185.5, 60 sec: 12356.3, 300 sec: 12367.8). Total num frames: 7658496. Throughput: 0: 12350.2. Samples: 6022608. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:40:39,314][1045180] Avg episode reward: [(0, '7.892')] -[2023-03-02 18:40:40,126][1045499] Updated weights for policy 0, policy_version 7489 (0.0006) -[2023-03-02 18:40:40,956][1045499] Updated weights for policy 0, policy_version 7499 (0.0007) -[2023-03-02 18:40:41,769][1045499] Updated weights for policy 0, policy_version 7509 (0.0006) -[2023-03-02 18:40:42,603][1045499] Updated weights for policy 0, policy_version 7519 (0.0008) -[2023-03-02 18:40:43,432][1045499] Updated weights for policy 0, policy_version 7529 (0.0007) -[2023-03-02 18:40:44,260][1045499] Updated weights for policy 0, policy_version 7539 (0.0006) -[2023-03-02 18:40:44,313][1045180] Fps is (10 sec: 12288.0, 60 sec: 12339.2, 300 sec: 12367.8). Total num frames: 7719936. Throughput: 0: 12347.9. Samples: 6059196. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:44,314][1045180] Avg episode reward: [(0, '7.893')] -[2023-03-02 18:40:45,078][1045499] Updated weights for policy 0, policy_version 7549 (0.0006) -[2023-03-02 18:40:45,912][1045499] Updated weights for policy 0, policy_version 7559 (0.0005) -[2023-03-02 18:40:46,742][1045499] Updated weights for policy 0, policy_version 7569 (0.0006) -[2023-03-02 18:40:47,555][1045499] Updated weights for policy 0, policy_version 7579 (0.0007) -[2023-03-02 18:40:48,386][1045499] Updated weights for policy 0, policy_version 7589 (0.0007) -[2023-03-02 18:40:49,204][1045499] Updated weights for policy 0, policy_version 7599 (0.0006) -[2023-03-02 18:40:49,313][1045180] Fps is (10 sec: 12390.4, 60 sec: 12356.2, 300 sec: 12367.8). Total num frames: 7782400. Throughput: 0: 12349.7. Samples: 6133737. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0) -[2023-03-02 18:40:49,314][1045180] Avg episode reward: [(0, '7.195')] -[2023-03-02 18:40:50,046][1045499] Updated weights for policy 0, policy_version 7609 (0.0007) -[2023-03-02 18:40:50,908][1045499] Updated weights for policy 0, policy_version 7619 (0.0006) -[2023-03-02 18:40:51,739][1045499] Updated weights for policy 0, policy_version 7629 (0.0006) -[2023-03-02 18:40:52,549][1045499] Updated weights for policy 0, policy_version 7639 (0.0007) -[2023-03-02 18:40:53,390][1045499] Updated weights for policy 0, policy_version 7649 (0.0006) -[2023-03-02 18:40:54,226][1045499] Updated weights for policy 0, policy_version 7659 (0.0006) -[2023-03-02 18:40:54,313][1045180] Fps is (10 sec: 12287.7, 60 sec: 12322.0, 300 sec: 12360.9). Total num frames: 7842816. Throughput: 0: 12345.7. Samples: 6207353. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:54,314][1045180] Avg episode reward: [(0, '8.553')] -[2023-03-02 18:40:55,052][1045499] Updated weights for policy 0, policy_version 7669 (0.0006) -[2023-03-02 18:40:55,893][1045499] Updated weights for policy 0, policy_version 7679 (0.0007) -[2023-03-02 18:40:56,714][1045499] Updated weights for policy 0, policy_version 7689 (0.0006) -[2023-03-02 18:40:57,575][1045499] Updated weights for policy 0, policy_version 7699 (0.0007) -[2023-03-02 18:40:58,393][1045499] Updated weights for policy 0, policy_version 7709 (0.0006) -[2023-03-02 18:40:59,224][1045499] Updated weights for policy 0, policy_version 7719 (0.0006) -[2023-03-02 18:40:59,313][1045180] Fps is (10 sec: 12185.6, 60 sec: 12322.1, 300 sec: 12360.9). Total num frames: 7904256. Throughput: 0: 12326.2. Samples: 6244117. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0) -[2023-03-02 18:40:59,314][1045180] Avg episode reward: [(0, '8.064')] -[2023-03-02 18:40:59,383][1045180] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1045180], exiting... -[2023-03-02 18:40:59,384][1045601] Stopping RolloutWorker_w10... -[2023-03-02 18:40:59,384][1045933] Stopping RolloutWorker_w27... -[2023-03-02 18:40:59,384][1045666] Stopping RolloutWorker_w8... -[2023-03-02 18:40:59,384][1045932] Stopping RolloutWorker_w28... -[2023-03-02 18:40:59,384][1045834] Stopping RolloutWorker_w22... -[2023-03-02 18:40:59,384][1045669] Stopping RolloutWorker_w17... -[2023-03-02 18:40:59,384][1045601] Loop rollout_proc10_evt_loop terminating... -[2023-03-02 18:40:59,384][1045770] Stopping RolloutWorker_w21... -[2023-03-02 18:40:59,384][1045670] Stopping RolloutWorker_w16... -[2023-03-02 18:40:59,384][1045706] Stopping RolloutWorker_w19... -[2023-03-02 18:40:59,384][1045503] Stopping RolloutWorker_w3... -[2023-03-02 18:40:59,384][1045667] Stopping RolloutWorker_w13... -[2023-03-02 18:40:59,384][1045504] Stopping RolloutWorker_w4... -[2023-03-02 18:40:59,384][1045738] Stopping RolloutWorker_w20... -[2023-03-02 18:40:59,385][1045666] Loop rollout_proc8_evt_loop terminating... -[2023-03-02 18:40:59,384][1045930] Stopping RolloutWorker_w26... -[2023-03-02 18:40:59,384][1045665] Stopping RolloutWorker_w9... -[2023-03-02 18:40:59,384][1045929] Stopping RolloutWorker_w24... -[2023-03-02 18:40:59,385][1045834] Loop rollout_proc22_evt_loop terminating... -[2023-03-02 18:40:59,385][1045933] Loop rollout_proc27_evt_loop terminating... -[2023-03-02 18:40:59,384][1045997] Stopping RolloutWorker_w30... -[2023-03-02 18:40:59,384][1045180] Runner profile tree view: -main_loop: 517.0250 -[2023-03-02 18:40:59,384][1045578] Stopping RolloutWorker_w7... -[2023-03-02 18:40:59,384][1045705] Stopping RolloutWorker_w15... -[2023-03-02 18:40:59,385][1045770] Loop rollout_proc21_evt_loop terminating... -[2023-03-02 18:40:59,385][1045932] Loop rollout_proc28_evt_loop terminating... -[2023-03-02 18:40:59,385][1045706] Loop rollout_proc19_evt_loop terminating... -[2023-03-02 18:40:59,385][1045503] Loop rollout_proc3_evt_loop terminating... -[2023-03-02 18:40:59,384][1045502] Stopping RolloutWorker_w2... -[2023-03-02 18:40:59,385][1045897] Stopping RolloutWorker_w23... -[2023-03-02 18:40:59,384][1045998] Stopping RolloutWorker_w25... -[2023-03-02 18:40:59,385][1045669] Loop rollout_proc17_evt_loop terminating... -[2023-03-02 18:40:59,385][1045670] Loop rollout_proc16_evt_loop terminating... -[2023-03-02 18:40:59,385][1045667] Loop rollout_proc13_evt_loop terminating... -[2023-03-02 18:40:59,385][1045930] Loop rollout_proc26_evt_loop terminating... -[2023-03-02 18:40:59,385][1045929] Loop rollout_proc24_evt_loop terminating... -[2023-03-02 18:40:59,385][1045997] Loop rollout_proc30_evt_loop terminating... -[2023-03-02 18:40:59,385][1045180] Collected {0: 7905280}, FPS: 12123.0 -[2023-03-02 18:40:59,385][1045578] Loop rollout_proc7_evt_loop terminating... -[2023-03-02 18:40:59,385][1045665] Loop rollout_proc9_evt_loop terminating... -[2023-03-02 18:40:59,385][1046030] Stopping RolloutWorker_w31... -[2023-03-02 18:40:59,384][1045671] Stopping RolloutWorker_w18... -[2023-03-02 18:40:59,385][1045897] Loop rollout_proc23_evt_loop terminating... -[2023-03-02 18:40:59,385][1045504] Loop rollout_proc4_evt_loop terminating... -[2023-03-02 18:40:59,385][1045705] Loop rollout_proc15_evt_loop terminating... -[2023-03-02 18:40:59,385][1045501] Stopping RolloutWorker_w1... -[2023-03-02 18:40:59,385][1045738] Loop rollout_proc20_evt_loop terminating... -[2023-03-02 18:40:59,385][1045664] Stopping RolloutWorker_w11... -[2023-03-02 18:40:59,385][1045502] Loop rollout_proc2_evt_loop terminating... -[2023-03-02 18:40:59,385][1045998] Loop rollout_proc25_evt_loop terminating... -[2023-03-02 18:40:59,385][1045501] Loop rollout_proc1_evt_loop terminating... -[2023-03-02 18:40:59,385][1045671] Loop rollout_proc18_evt_loop terminating... -[2023-03-02 18:40:59,385][1045664] Loop rollout_proc11_evt_loop terminating... -[2023-03-02 18:40:59,385][1045668] Stopping RolloutWorker_w12... -[2023-03-02 18:40:59,385][1046030] Loop rollout_proc31_evt_loop terminating... -[2023-03-02 18:40:59,386][1045668] Loop rollout_proc12_evt_loop terminating... -[2023-03-02 18:40:59,386][1045965] Stopping RolloutWorker_w29... -[2023-03-02 18:40:59,389][1045965] Loop rollout_proc29_evt_loop terminating... -[2023-03-02 18:40:59,390][1045505] Stopping RolloutWorker_w5... -[2023-03-02 18:40:59,391][1045505] Loop rollout_proc5_evt_loop terminating... -[2023-03-02 18:40:59,399][1045507] Stopping RolloutWorker_w6... -[2023-03-02 18:40:59,400][1045507] Loop rollout_proc6_evt_loop terminating... -[2023-03-02 18:40:59,400][1045448] Stopping Batcher_0... -[2023-03-02 18:40:59,401][1045448] Loop batcher_evt_loop terminating... -[2023-03-02 18:40:59,401][1045500] Stopping RolloutWorker_w0... -[2023-03-02 18:40:59,402][1045500] Loop rollout_proc0_evt_loop terminating... -[2023-03-02 18:40:59,406][1045673] Stopping RolloutWorker_w14... -[2023-03-02 18:40:59,407][1045673] Loop rollout_proc14_evt_loop terminating... -[2023-03-02 18:40:59,423][1045448] Saving /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000007721_7906304.pth... -[2023-03-02 18:40:59,452][1045499] Weights refcount: 2 0 -[2023-03-02 18:40:59,454][1045499] Stopping InferenceWorker_p0-w0... -[2023-03-02 18:40:59,454][1045499] Loop inference_proc0-0_evt_loop terminating... -[2023-03-02 18:40:59,537][1045448] Removing /home/qgallouedec/train_dir/default_experiment/checkpoint_p0/checkpoint_000005790_5928960.pth -[2023-03-02 18:40:59,545][1045448] Stopping LearnerWorker_p0... -[2023-03-02 18:40:59,545][1045448] Loop learner_proc0_evt_loop terminating... +[2023-03-03 11:19:43,686][17030] Using optimizer +[2023-03-03 11:19:43,687][17030] No checkpoints found +[2023-03-03 11:19:43,688][17030] Did not load from checkpoint, starting from scratch! +[2023-03-03 11:19:43,693][17030] Initialized policy 0 weights for model version 0 +[2023-03-03 11:19:43,694][17030] LearnerWorker_p0 finished initialization! +[2023-03-03 11:19:43,752][17038] On MacOS, not setting affinity +[2023-03-03 11:19:43,813][17032] On MacOS, not setting affinity +[2023-03-03 11:19:43,816][17031] RunningMeanStd input shape: (39,) +[2023-03-03 11:19:43,817][17031] RunningMeanStd input shape: (1,) +[2023-03-03 11:19:43,835][17036] On MacOS, not setting affinity +[2023-03-03 11:19:43,846][17033] On MacOS, not setting affinity +[2023-03-03 11:19:43,846][17035] On MacOS, not setting affinity +[2023-03-03 11:19:43,875][16994] Inference worker 0-0 is ready! +[2023-03-03 11:19:43,877][16994] All inference workers are ready! Signal rollout workers to start! +[2023-03-03 11:19:44,848][17039] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,883][17037] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,883][17032] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,932][17038] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,935][17034] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,966][17035] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,969][17033] Decorrelating experience for 0 frames... +[2023-03-03 11:19:44,995][17036] Decorrelating experience for 0 frames... +[2023-03-03 11:19:45,824][17037] Decorrelating experience for 32 frames... +[2023-03-03 11:19:45,846][17032] Decorrelating experience for 32 frames... +[2023-03-03 11:19:45,898][17038] Decorrelating experience for 32 frames... +[2023-03-03 11:19:45,938][17034] Decorrelating experience for 32 frames... +[2023-03-03 11:19:45,946][17033] Decorrelating experience for 32 frames... +[2023-03-03 11:19:45,992][17036] Decorrelating experience for 32 frames... +[2023-03-03 11:19:46,027][17035] Decorrelating experience for 32 frames... +[2023-03-03 11:19:46,047][17039] Decorrelating experience for 32 frames... +[2023-03-03 11:19:47,683][16994] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4096. Throughput: 0: nan. Samples: 2914. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-03-03 11:19:49,484][17031] Updated weights for policy 0, policy_version 10 (0.0008) +[2023-03-03 11:19:52,621][17031] Updated weights for policy 0, policy_version 20 (0.0007) +[2023-03-03 11:19:52,682][16994] Fps is (10 sec: 3277.0, 60 sec: 3277.0, 300 sec: 3277.0). Total num frames: 20480. Throughput: 0: 1888.9. Samples: 12358. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:19:52,683][16994] Avg episode reward: [(0, '4.341')] +[2023-03-03 11:19:55,978][17031] Updated weights for policy 0, policy_version 30 (0.0008) +[2023-03-03 11:19:57,684][16994] Fps is (10 sec: 3174.0, 60 sec: 3174.0, 300 sec: 3174.0). Total num frames: 35840. Throughput: 0: 2828.4. Samples: 31202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-03-03 11:19:57,685][16994] Avg episode reward: [(0, '5.303')] +[2023-03-03 11:19:59,217][17031] Updated weights for policy 0, policy_version 40 (0.0006) +[2023-03-03 11:19:59,664][16994] Heartbeat connected on Batcher_0 +[2023-03-03 11:19:59,681][16994] Heartbeat connected on InferenceWorker_p0-w0 +[2023-03-03 11:19:59,683][16994] Heartbeat connected on RolloutWorker_w0 +[2023-03-03 11:19:59,687][16994] Heartbeat connected on RolloutWorker_w1 +[2023-03-03 11:19:59,691][16994] Heartbeat connected on RolloutWorker_w2 +[2023-03-03 11:19:59,696][16994] Heartbeat connected on RolloutWorker_w3 +[2023-03-03 11:19:59,702][16994] Heartbeat connected on RolloutWorker_w4 +[2023-03-03 11:19:59,707][16994] Heartbeat connected on RolloutWorker_w5 +[2023-03-03 11:19:59,718][16994] Heartbeat connected on RolloutWorker_w6 +[2023-03-03 11:19:59,721][16994] Heartbeat connected on RolloutWorker_w7 +[2023-03-03 11:19:59,864][16994] Heartbeat connected on LearnerWorker_p0 +[2023-03-03 11:20:02,508][17031] Updated weights for policy 0, policy_version 50 (0.0008) +[2023-03-03 11:20:02,681][16994] Fps is (10 sec: 3072.4, 60 sec: 3140.6, 300 sec: 3140.6). Total num frames: 51200. Throughput: 0: 3133.0. Samples: 49904. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:20:02,682][16994] Avg episode reward: [(0, '5.930')] +[2023-03-03 11:20:05,680][17031] Updated weights for policy 0, policy_version 60 (0.0007) +[2023-03-03 11:20:07,681][16994] Fps is (10 sec: 3175.4, 60 sec: 3174.7, 300 sec: 3174.7). Total num frames: 67584. Throughput: 0: 2827.8. Samples: 59466. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:20:07,681][16994] Avg episode reward: [(0, '6.461')] +[2023-03-03 11:20:08,979][17031] Updated weights for policy 0, policy_version 70 (0.0006) +[2023-03-03 11:20:12,410][17031] Updated weights for policy 0, policy_version 80 (0.0009) +[2023-03-03 11:20:12,685][16994] Fps is (10 sec: 3070.9, 60 sec: 3112.7, 300 sec: 3112.7). Total num frames: 81920. Throughput: 0: 3011.7. Samples: 78213. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:20:12,688][16994] Avg episode reward: [(0, '6.726')] +[2023-03-03 11:20:16,059][17031] Updated weights for policy 0, policy_version 90 (0.0009) +[2023-03-03 11:20:17,682][16994] Fps is (10 sec: 2764.5, 60 sec: 3037.9, 300 sec: 3037.9). Total num frames: 95232. Throughput: 0: 3050.6. Samples: 94430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-03-03 11:20:17,685][16994] Avg episode reward: [(0, '6.601')] +[2023-03-03 11:20:19,878][17031] Updated weights for policy 0, policy_version 100 (0.0007) +[2023-03-03 11:20:22,682][16994] Fps is (10 sec: 2765.4, 60 sec: 3013.5, 300 sec: 3013.5). Total num frames: 109568. Throughput: 0: 2863.2. Samples: 103126. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:20:22,685][16994] Avg episode reward: [(0, '6.769')] +[2023-03-03 11:20:22,734][17030] Saving new best policy, reward=6.769! +[2023-03-03 11:20:23,564][17031] Updated weights for policy 0, policy_version 110 (0.0008) +[2023-03-03 11:20:26,793][17031] Updated weights for policy 0, policy_version 120 (0.0008) +[2023-03-03 11:20:27,684][16994] Fps is (10 sec: 2969.1, 60 sec: 3020.7, 300 sec: 3020.7). Total num frames: 124928. Throughput: 0: 2944.1. Samples: 120681. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:20:27,685][16994] Avg episode reward: [(0, '7.823')] +[2023-03-03 11:20:27,751][17030] Saving new best policy, reward=7.823! +[2023-03-03 11:20:30,017][17031] Updated weights for policy 0, policy_version 130 (0.0006) +[2023-03-03 11:20:32,683][16994] Fps is (10 sec: 3174.2, 60 sec: 3049.2, 300 sec: 3049.2). Total num frames: 141312. Throughput: 0: 3038.5. Samples: 139649. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:20:32,684][16994] Avg episode reward: [(0, '8.973')] +[2023-03-03 11:20:32,684][17030] Saving new best policy, reward=8.973! +[2023-03-03 11:20:33,250][17031] Updated weights for policy 0, policy_version 140 (0.0007) +[2023-03-03 11:20:36,407][17031] Updated weights for policy 0, policy_version 150 (0.0007) +[2023-03-03 11:20:37,682][16994] Fps is (10 sec: 3277.3, 60 sec: 3072.0, 300 sec: 3072.0). Total num frames: 157696. Throughput: 0: 3039.4. Samples: 149131. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:20:37,683][16994] Avg episode reward: [(0, '10.288')] +[2023-03-03 11:20:37,688][17030] Saving new best policy, reward=10.288! +[2023-03-03 11:20:39,529][17031] Updated weights for policy 0, policy_version 160 (0.0007) +[2023-03-03 11:20:42,684][16994] Fps is (10 sec: 3071.8, 60 sec: 3053.3, 300 sec: 3053.3). Total num frames: 172032. Throughput: 0: 3028.3. Samples: 167475. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:20:42,685][16994] Avg episode reward: [(0, '10.363')] +[2023-03-03 11:20:42,686][17030] Saving new best policy, reward=10.363! +[2023-03-03 11:20:43,362][17031] Updated weights for policy 0, policy_version 170 (0.0009) +[2023-03-03 11:20:46,966][17031] Updated weights for policy 0, policy_version 180 (0.0007) +[2023-03-03 11:20:47,683][16994] Fps is (10 sec: 2867.2, 60 sec: 3037.9, 300 sec: 3037.9). Total num frames: 186368. Throughput: 0: 3000.2. Samples: 184916. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:20:47,685][16994] Avg episode reward: [(0, '11.854')] +[2023-03-03 11:20:47,689][17030] Saving new best policy, reward=11.854! +[2023-03-03 11:20:51,032][17031] Updated weights for policy 0, policy_version 190 (0.0008) +[2023-03-03 11:20:52,683][16994] Fps is (10 sec: 2560.2, 60 sec: 2952.5, 300 sec: 2977.5). Total num frames: 197632. Throughput: 0: 2959.4. Samples: 192647. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-03-03 11:20:52,686][16994] Avg episode reward: [(0, '11.889')] +[2023-03-03 11:20:52,719][17030] Saving new best policy, reward=11.889! +[2023-03-03 11:20:54,924][17031] Updated weights for policy 0, policy_version 200 (0.0008) +[2023-03-03 11:20:57,683][16994] Fps is (10 sec: 2662.3, 60 sec: 2952.6, 300 sec: 2984.2). Total num frames: 212992. Throughput: 0: 2898.2. Samples: 208629. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:20:57,685][16994] Avg episode reward: [(0, '13.343')] +[2023-03-03 11:20:57,691][17030] Saving new best policy, reward=13.343! +[2023-03-03 11:20:58,304][17031] Updated weights for policy 0, policy_version 210 (0.0013) +[2023-03-03 11:21:02,239][17031] Updated weights for policy 0, policy_version 220 (0.0010) +[2023-03-03 11:21:02,683][16994] Fps is (10 sec: 2867.1, 60 sec: 2918.3, 300 sec: 2962.8). Total num frames: 226304. Throughput: 0: 2909.3. Samples: 225350. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:21:02,685][16994] Avg episode reward: [(0, '14.866')] +[2023-03-03 11:21:02,686][17030] Saving new best policy, reward=14.866! +[2023-03-03 11:21:05,679][17031] Updated weights for policy 0, policy_version 230 (0.0007) +[2023-03-03 11:21:07,683][16994] Fps is (10 sec: 2764.7, 60 sec: 2884.1, 300 sec: 2956.8). Total num frames: 240640. Throughput: 0: 2904.5. Samples: 233833. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:21:07,684][16994] Avg episode reward: [(0, '15.002')] +[2023-03-03 11:21:07,767][17030] Saving new best policy, reward=15.002! +[2023-03-03 11:21:09,100][17031] Updated weights for policy 0, policy_version 240 (0.0007) +[2023-03-03 11:21:12,427][17031] Updated weights for policy 0, policy_version 250 (0.0009) +[2023-03-03 11:21:12,682][16994] Fps is (10 sec: 2970.0, 60 sec: 2901.5, 300 sec: 2963.6). Total num frames: 256000. Throughput: 0: 2922.0. Samples: 252164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:21:12,683][16994] Avg episode reward: [(0, '15.373')] +[2023-03-03 11:21:12,748][17030] Saving new best policy, reward=15.373! +[2023-03-03 11:21:15,846][17031] Updated weights for policy 0, policy_version 260 (0.0007) +[2023-03-03 11:21:17,685][16994] Fps is (10 sec: 2969.2, 60 sec: 2918.3, 300 sec: 2958.2). Total num frames: 270336. Throughput: 0: 2890.5. Samples: 269724. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:21:17,687][16994] Avg episode reward: [(0, '14.800')] +[2023-03-03 11:21:19,480][17031] Updated weights for policy 0, policy_version 270 (0.0009) +[2023-03-03 11:21:22,684][16994] Fps is (10 sec: 2866.6, 60 sec: 2918.3, 300 sec: 2953.4). Total num frames: 284672. Throughput: 0: 2871.5. Samples: 278353. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:21:22,687][16994] Avg episode reward: [(0, '14.436')] +[2023-03-03 11:21:23,184][17031] Updated weights for policy 0, policy_version 280 (0.0007) +[2023-03-03 11:21:27,106][17031] Updated weights for policy 0, policy_version 290 (0.0008) +[2023-03-03 11:21:27,684][16994] Fps is (10 sec: 2764.9, 60 sec: 2884.2, 300 sec: 2938.8). Total num frames: 297984. Throughput: 0: 2818.6. Samples: 294315. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:21:27,687][16994] Avg episode reward: [(0, '14.826')] +[2023-03-03 11:21:30,845][17031] Updated weights for policy 0, policy_version 300 (0.0007) +[2023-03-03 11:21:32,685][16994] Fps is (10 sec: 2559.8, 60 sec: 2815.9, 300 sec: 2915.9). Total num frames: 310272. Throughput: 0: 2779.1. Samples: 309983. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:21:32,688][16994] Avg episode reward: [(0, '15.389')] +[2023-03-03 11:21:32,695][17030] Saving new best policy, reward=15.389! +[2023-03-03 11:21:34,888][17031] Updated weights for policy 0, policy_version 310 (0.0010) +[2023-03-03 11:21:37,685][16994] Fps is (10 sec: 2662.3, 60 sec: 2781.8, 300 sec: 2913.7). Total num frames: 324608. Throughput: 0: 2787.5. Samples: 318090. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:21:37,686][16994] Avg episode reward: [(0, '16.356')] +[2023-03-03 11:21:37,835][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000318_325632.pth... +[2023-03-03 11:21:37,925][17030] Saving new best policy, reward=16.356! +[2023-03-03 11:21:38,517][17031] Updated weights for policy 0, policy_version 320 (0.0008) +[2023-03-03 11:21:42,684][16994] Fps is (10 sec: 2662.6, 60 sec: 2747.7, 300 sec: 2893.9). Total num frames: 336896. Throughput: 0: 2790.7. Samples: 334213. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:21:42,686][16994] Avg episode reward: [(0, '18.428')] +[2023-03-03 11:21:42,687][17030] Saving new best policy, reward=18.428! +[2023-03-03 11:21:42,949][17031] Updated weights for policy 0, policy_version 330 (0.0018) +[2023-03-03 11:21:46,353][17031] Updated weights for policy 0, policy_version 340 (0.0007) +[2023-03-03 11:21:47,683][16994] Fps is (10 sec: 2662.9, 60 sec: 2747.7, 300 sec: 2892.8). Total num frames: 351232. Throughput: 0: 2781.5. Samples: 350515. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:21:47,686][16994] Avg episode reward: [(0, '20.106')] +[2023-03-03 11:21:47,831][17030] Saving new best policy, reward=20.106! +[2023-03-03 11:21:50,300][17031] Updated weights for policy 0, policy_version 350 (0.0008) +[2023-03-03 11:21:52,684][16994] Fps is (10 sec: 2867.1, 60 sec: 2798.9, 300 sec: 2891.7). Total num frames: 365568. Throughput: 0: 2760.1. Samples: 358039. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:21:52,687][16994] Avg episode reward: [(0, '20.657')] +[2023-03-03 11:21:52,795][17030] Saving new best policy, reward=20.657! +[2023-03-03 11:21:53,533][17031] Updated weights for policy 0, policy_version 360 (0.0008) +[2023-03-03 11:21:56,808][17031] Updated weights for policy 0, policy_version 370 (0.0007) +[2023-03-03 11:21:57,681][16994] Fps is (10 sec: 2970.2, 60 sec: 2799.0, 300 sec: 2898.7). Total num frames: 380928. Throughput: 0: 2761.0. Samples: 376406. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:21:57,681][16994] Avg episode reward: [(0, '21.310')] +[2023-03-03 11:21:57,689][17030] Saving new best policy, reward=21.310! +[2023-03-03 11:22:00,298][17031] Updated weights for policy 0, policy_version 380 (0.0008) +[2023-03-03 11:22:02,683][16994] Fps is (10 sec: 3072.3, 60 sec: 2833.1, 300 sec: 2905.1). Total num frames: 396288. Throughput: 0: 2778.3. Samples: 394744. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:22:02,684][16994] Avg episode reward: [(0, '22.168')] +[2023-03-03 11:22:02,685][17030] Saving new best policy, reward=22.168! +[2023-03-03 11:22:03,531][17031] Updated weights for policy 0, policy_version 390 (0.0008) +[2023-03-03 11:22:06,890][17031] Updated weights for policy 0, policy_version 400 (0.0008) +[2023-03-03 11:22:07,683][16994] Fps is (10 sec: 3071.2, 60 sec: 2850.1, 300 sec: 2911.1). Total num frames: 411648. Throughput: 0: 2796.3. Samples: 404187. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:22:07,684][16994] Avg episode reward: [(0, '21.111')] +[2023-03-03 11:22:10,690][17031] Updated weights for policy 0, policy_version 410 (0.0016) +[2023-03-03 11:22:12,683][16994] Fps is (10 sec: 2764.7, 60 sec: 2798.9, 300 sec: 2895.4). Total num frames: 423936. Throughput: 0: 2824.0. Samples: 421391. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:12,686][16994] Avg episode reward: [(0, '27.536')] +[2023-03-03 11:22:12,690][17030] Saving new best policy, reward=27.536! +[2023-03-03 11:22:14,185][17031] Updated weights for policy 0, policy_version 420 (0.0007) +[2023-03-03 11:22:17,683][16994] Fps is (10 sec: 2764.9, 60 sec: 2816.1, 300 sec: 2901.3). Total num frames: 439296. Throughput: 0: 2865.4. Samples: 438923. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:22:17,684][16994] Avg episode reward: [(0, '27.382')] +[2023-03-03 11:22:17,819][17031] Updated weights for policy 0, policy_version 430 (0.0007) +[2023-03-03 11:22:21,346][17031] Updated weights for policy 0, policy_version 440 (0.0008) +[2023-03-03 11:22:22,682][16994] Fps is (10 sec: 3072.6, 60 sec: 2833.2, 300 sec: 2906.9). Total num frames: 454656. Throughput: 0: 2881.6. Samples: 447751. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:22,697][16994] Avg episode reward: [(0, '28.442')] +[2023-03-03 11:22:22,867][17030] Saving new best policy, reward=28.442! +[2023-03-03 11:22:25,095][17031] Updated weights for policy 0, policy_version 450 (0.0008) +[2023-03-03 11:22:27,684][16994] Fps is (10 sec: 2867.0, 60 sec: 2833.1, 300 sec: 2899.2). Total num frames: 467968. Throughput: 0: 2869.5. Samples: 463342. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:22:27,686][16994] Avg episode reward: [(0, '23.001')] +[2023-03-03 11:22:28,598][17031] Updated weights for policy 0, policy_version 460 (0.0007) +[2023-03-03 11:22:31,685][17031] Updated weights for policy 0, policy_version 470 (0.0007) +[2023-03-03 11:22:32,683][16994] Fps is (10 sec: 2969.0, 60 sec: 2901.4, 300 sec: 2910.6). Total num frames: 484352. Throughput: 0: 2941.1. Samples: 482865. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:32,684][16994] Avg episode reward: [(0, '23.627')] +[2023-03-03 11:22:34,951][17031] Updated weights for policy 0, policy_version 480 (0.0007) +[2023-03-03 11:22:37,684][16994] Fps is (10 sec: 3071.9, 60 sec: 2901.4, 300 sec: 2909.3). Total num frames: 498688. Throughput: 0: 2978.7. Samples: 492082. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:22:37,686][16994] Avg episode reward: [(0, '24.366')] +[2023-03-03 11:22:38,503][17031] Updated weights for policy 0, policy_version 490 (0.0008) +[2023-03-03 11:22:42,203][17031] Updated weights for policy 0, policy_version 500 (0.0010) +[2023-03-03 11:22:42,683][16994] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2908.2). Total num frames: 513024. Throughput: 0: 2958.1. Samples: 509528. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:22:42,685][16994] Avg episode reward: [(0, '25.101')] +[2023-03-03 11:22:45,721][17031] Updated weights for policy 0, policy_version 510 (0.0007) +[2023-03-03 11:22:47,683][16994] Fps is (10 sec: 2867.6, 60 sec: 2935.5, 300 sec: 2907.0). Total num frames: 527360. Throughput: 0: 2929.4. Samples: 526565. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:47,684][16994] Avg episode reward: [(0, '26.304')] +[2023-03-03 11:22:49,180][17031] Updated weights for policy 0, policy_version 520 (0.0009) +[2023-03-03 11:22:52,382][17031] Updated weights for policy 0, policy_version 530 (0.0008) +[2023-03-03 11:22:52,683][16994] Fps is (10 sec: 2969.5, 60 sec: 2952.6, 300 sec: 2911.5). Total num frames: 542720. Throughput: 0: 2913.9. Samples: 535311. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:52,685][16994] Avg episode reward: [(0, '27.157')] +[2023-03-03 11:22:55,888][17031] Updated weights for policy 0, policy_version 540 (0.0007) +[2023-03-03 11:22:57,681][16994] Fps is (10 sec: 3175.1, 60 sec: 2969.6, 300 sec: 2921.1). Total num frames: 559104. Throughput: 0: 2941.3. Samples: 553743. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:22:57,682][16994] Avg episode reward: [(0, '28.972')] +[2023-03-03 11:22:57,690][17030] Saving new best policy, reward=28.972! +[2023-03-03 11:22:58,986][17031] Updated weights for policy 0, policy_version 550 (0.0007) +[2023-03-03 11:23:02,056][17031] Updated weights for policy 0, policy_version 560 (0.0007) +[2023-03-03 11:23:02,683][16994] Fps is (10 sec: 3276.8, 60 sec: 2986.7, 300 sec: 2930.2). Total num frames: 575488. Throughput: 0: 2994.2. Samples: 573661. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:23:02,684][16994] Avg episode reward: [(0, '30.927')] +[2023-03-03 11:23:02,684][17030] Saving new best policy, reward=30.927! +[2023-03-03 11:23:05,153][17031] Updated weights for policy 0, policy_version 570 (0.0007) +[2023-03-03 11:23:07,682][16994] Fps is (10 sec: 3173.9, 60 sec: 2986.7, 300 sec: 2933.8). Total num frames: 590848. Throughput: 0: 3024.4. Samples: 583852. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:07,684][16994] Avg episode reward: [(0, '31.405')] +[2023-03-03 11:23:07,868][17030] Saving new best policy, reward=31.405! +[2023-03-03 11:23:08,519][17031] Updated weights for policy 0, policy_version 580 (0.0007) +[2023-03-03 11:23:12,150][17031] Updated weights for policy 0, policy_version 590 (0.0010) +[2023-03-03 11:23:12,681][16994] Fps is (10 sec: 2970.4, 60 sec: 3020.9, 300 sec: 2932.2). Total num frames: 605184. Throughput: 0: 3077.5. Samples: 601821. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:23:12,683][16994] Avg episode reward: [(0, '32.142')] +[2023-03-03 11:23:12,842][17030] Saving new best policy, reward=32.142! +[2023-03-03 11:23:15,561][17031] Updated weights for policy 0, policy_version 600 (0.0007) +[2023-03-03 11:23:17,703][16994] Fps is (10 sec: 2861.2, 60 sec: 3002.7, 300 sec: 2930.3). Total num frames: 619520. Throughput: 0: 3026.6. Samples: 619123. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:17,727][16994] Avg episode reward: [(0, '30.425')] +[2023-03-03 11:23:19,316][17031] Updated weights for policy 0, policy_version 610 (0.0009) +[2023-03-03 11:23:22,641][17031] Updated weights for policy 0, policy_version 620 (0.0010) +[2023-03-03 11:23:22,681][16994] Fps is (10 sec: 2969.5, 60 sec: 3003.8, 300 sec: 2933.9). Total num frames: 634880. Throughput: 0: 2999.8. Samples: 627064. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:22,681][16994] Avg episode reward: [(0, '31.084')] +[2023-03-03 11:23:27,305][17031] Updated weights for policy 0, policy_version 630 (0.0010) +[2023-03-03 11:23:27,690][16994] Fps is (10 sec: 2666.5, 60 sec: 2969.4, 300 sec: 2918.3). Total num frames: 646144. Throughput: 0: 2942.3. Samples: 641943. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:23:27,694][16994] Avg episode reward: [(0, '33.239')] +[2023-03-03 11:23:27,701][17030] Saving new best policy, reward=33.239! +[2023-03-03 11:23:31,042][17031] Updated weights for policy 0, policy_version 640 (0.0007) +[2023-03-03 11:23:32,682][16994] Fps is (10 sec: 2354.8, 60 sec: 2901.4, 300 sec: 2908.2). Total num frames: 658432. Throughput: 0: 2921.9. Samples: 658047. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:23:32,687][16994] Avg episode reward: [(0, '35.241')] +[2023-03-03 11:23:32,692][17030] Saving new best policy, reward=35.241! +[2023-03-03 11:23:34,624][17031] Updated weights for policy 0, policy_version 650 (0.0007) +[2023-03-03 11:23:37,683][16994] Fps is (10 sec: 2766.0, 60 sec: 2918.4, 300 sec: 2911.7). Total num frames: 673792. Throughput: 0: 2931.5. Samples: 667231. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:37,685][16994] Avg episode reward: [(0, '36.570')] +[2023-03-03 11:23:37,832][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000659_674816.pth... +[2023-03-03 11:23:37,881][17030] Saving new best policy, reward=36.570! +[2023-03-03 11:23:38,157][17031] Updated weights for policy 0, policy_version 660 (0.0007) +[2023-03-03 11:23:41,391][17031] Updated weights for policy 0, policy_version 670 (0.0007) +[2023-03-03 11:23:42,684][16994] Fps is (10 sec: 2969.2, 60 sec: 2918.4, 300 sec: 2910.8). Total num frames: 688128. Throughput: 0: 2922.6. Samples: 685271. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:42,688][16994] Avg episode reward: [(0, '36.296')] +[2023-03-03 11:23:45,880][17031] Updated weights for policy 0, policy_version 680 (0.0010) +[2023-03-03 11:23:47,689][16994] Fps is (10 sec: 2662.2, 60 sec: 2884.2, 300 sec: 2901.3). Total num frames: 700416. Throughput: 0: 2813.8. Samples: 700286. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:23:47,699][16994] Avg episode reward: [(0, '36.345')] +[2023-03-03 11:23:49,728][17031] Updated weights for policy 0, policy_version 690 (0.0007) +[2023-03-03 11:23:52,684][16994] Fps is (10 sec: 2560.1, 60 sec: 2850.1, 300 sec: 2896.4). Total num frames: 713728. Throughput: 0: 2757.5. Samples: 707942. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:23:52,688][16994] Avg episode reward: [(0, '35.173')] +[2023-03-03 11:23:53,667][17031] Updated weights for policy 0, policy_version 700 (0.0009) +[2023-03-03 11:23:57,043][17031] Updated weights for policy 0, policy_version 710 (0.0007) +[2023-03-03 11:23:57,681][16994] Fps is (10 sec: 2765.6, 60 sec: 2816.0, 300 sec: 2895.9). Total num frames: 728064. Throughput: 0: 2725.5. Samples: 724470. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:23:57,685][16994] Avg episode reward: [(0, '36.033')] +[2023-03-03 11:24:00,257][17031] Updated weights for policy 0, policy_version 720 (0.0007) +[2023-03-03 11:24:02,683][16994] Fps is (10 sec: 3072.1, 60 sec: 2816.0, 300 sec: 2903.3). Total num frames: 744448. Throughput: 0: 2760.8. Samples: 743303. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:24:02,684][16994] Avg episode reward: [(0, '38.665')] +[2023-03-03 11:24:02,754][17030] Saving new best policy, reward=38.665! +[2023-03-03 11:24:03,571][17031] Updated weights for policy 0, policy_version 730 (0.0007) +[2023-03-03 11:24:06,817][17031] Updated weights for policy 0, policy_version 740 (0.0009) +[2023-03-03 11:24:07,684][16994] Fps is (10 sec: 3071.3, 60 sec: 2798.9, 300 sec: 2902.6). Total num frames: 758784. Throughput: 0: 2784.8. Samples: 752387. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:24:07,686][16994] Avg episode reward: [(0, '40.911')] +[2023-03-03 11:24:07,744][17030] Saving new best policy, reward=40.911! +[2023-03-03 11:24:10,557][17031] Updated weights for policy 0, policy_version 750 (0.0007) +[2023-03-03 11:24:12,682][16994] Fps is (10 sec: 2970.0, 60 sec: 2815.9, 300 sec: 2905.9). Total num frames: 774144. Throughput: 0: 2842.3. Samples: 769832. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:24:12,684][16994] Avg episode reward: [(0, '39.414')] +[2023-03-03 11:24:13,705][17031] Updated weights for policy 0, policy_version 760 (0.0007) +[2023-03-03 11:24:16,956][17031] Updated weights for policy 0, policy_version 770 (0.0006) +[2023-03-03 11:24:17,681][16994] Fps is (10 sec: 3175.2, 60 sec: 2851.2, 300 sec: 2912.7). Total num frames: 790528. Throughput: 0: 2912.3. Samples: 789099. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:24:17,682][16994] Avg episode reward: [(0, '38.017')] +[2023-03-03 11:24:20,225][17031] Updated weights for policy 0, policy_version 780 (0.0007) +[2023-03-03 11:24:22,683][16994] Fps is (10 sec: 3173.9, 60 sec: 2850.0, 300 sec: 2915.6). Total num frames: 805888. Throughput: 0: 2919.1. Samples: 798590. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:24:22,715][16994] Avg episode reward: [(0, '34.144')] +[2023-03-03 11:24:24,004][17031] Updated weights for policy 0, policy_version 790 (0.0009) +[2023-03-03 11:24:27,681][16994] Fps is (10 sec: 2764.9, 60 sec: 2867.5, 300 sec: 2907.4). Total num frames: 818176. Throughput: 0: 2878.1. Samples: 814775. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:24:27,682][16994] Avg episode reward: [(0, '33.307')] +[2023-03-03 11:24:27,916][17031] Updated weights for policy 0, policy_version 800 (0.0018) +[2023-03-03 11:24:31,677][17031] Updated weights for policy 0, policy_version 810 (0.0009) +[2023-03-03 11:24:32,683][16994] Fps is (10 sec: 2560.2, 60 sec: 2884.3, 300 sec: 2903.1). Total num frames: 831488. Throughput: 0: 2898.5. Samples: 830715. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:24:32,685][16994] Avg episode reward: [(0, '36.157')] +[2023-03-03 11:24:35,673][17031] Updated weights for policy 0, policy_version 820 (0.0008) +[2023-03-03 11:24:37,683][16994] Fps is (10 sec: 2457.2, 60 sec: 2816.0, 300 sec: 2891.9). Total num frames: 842752. Throughput: 0: 2909.6. Samples: 838873. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:24:37,686][16994] Avg episode reward: [(0, '36.837')] +[2023-03-03 11:24:39,860][17031] Updated weights for policy 0, policy_version 830 (0.0007) +[2023-03-03 11:24:42,684][16994] Fps is (10 sec: 2661.9, 60 sec: 2833.0, 300 sec: 2895.0). Total num frames: 858112. Throughput: 0: 2868.5. Samples: 853563. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) +[2023-03-03 11:24:42,686][16994] Avg episode reward: [(0, '38.594')] +[2023-03-03 11:24:43,352][17031] Updated weights for policy 0, policy_version 840 (0.0008) +[2023-03-03 11:24:46,685][17031] Updated weights for policy 0, policy_version 850 (0.0007) +[2023-03-03 11:24:47,684][16994] Fps is (10 sec: 2969.1, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 872448. Throughput: 0: 2854.9. Samples: 871778. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:24:47,685][16994] Avg episode reward: [(0, '75.849')] +[2023-03-03 11:24:47,749][17030] Saving new best policy, reward=75.849! +[2023-03-03 11:24:49,993][17031] Updated weights for policy 0, policy_version 860 (0.0006) +[2023-03-03 11:24:52,682][16994] Fps is (10 sec: 2970.3, 60 sec: 2901.4, 300 sec: 2888.0). Total num frames: 887808. Throughput: 0: 2861.7. Samples: 881159. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:24:52,683][16994] Avg episode reward: [(0, '68.514')] +[2023-03-03 11:24:53,447][17031] Updated weights for policy 0, policy_version 870 (0.0007) +[2023-03-03 11:24:56,946][17031] Updated weights for policy 0, policy_version 880 (0.0007) +[2023-03-03 11:24:57,682][16994] Fps is (10 sec: 3072.8, 60 sec: 2918.4, 300 sec: 2888.0). Total num frames: 903168. Throughput: 0: 2869.7. Samples: 898967. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:24:57,684][16994] Avg episode reward: [(0, '62.574')] +[2023-03-03 11:25:00,524][17031] Updated weights for policy 0, policy_version 890 (0.0008) +[2023-03-03 11:25:02,684][16994] Fps is (10 sec: 2866.8, 60 sec: 2867.2, 300 sec: 2877.6). Total num frames: 916480. Throughput: 0: 2816.2. Samples: 915833. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:25:02,686][16994] Avg episode reward: [(0, '24.017')] +[2023-03-03 11:25:04,142][17031] Updated weights for policy 0, policy_version 900 (0.0008) +[2023-03-03 11:25:07,639][17031] Updated weights for policy 0, policy_version 910 (0.0008) +[2023-03-03 11:25:07,682][16994] Fps is (10 sec: 2867.2, 60 sec: 2884.4, 300 sec: 2881.1). Total num frames: 931840. Throughput: 0: 2794.2. Samples: 924326. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:25:07,683][16994] Avg episode reward: [(0, '28.655')] +[2023-03-03 11:25:10,859][17031] Updated weights for policy 0, policy_version 920 (0.0007) +[2023-03-03 11:25:12,682][16994] Fps is (10 sec: 3072.5, 60 sec: 2884.3, 300 sec: 2888.0). Total num frames: 947200. Throughput: 0: 2848.7. Samples: 942970. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:25:12,682][16994] Avg episode reward: [(0, '31.668')] +[2023-03-03 11:25:14,066][17031] Updated weights for policy 0, policy_version 930 (0.0006) +[2023-03-03 11:25:17,074][17031] Updated weights for policy 0, policy_version 940 (0.0007) +[2023-03-03 11:25:17,682][16994] Fps is (10 sec: 3174.1, 60 sec: 2884.2, 300 sec: 2895.0). Total num frames: 963584. Throughput: 0: 2933.8. Samples: 962737. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:25:17,684][16994] Avg episode reward: [(0, '32.671')] +[2023-03-03 11:25:20,145][17031] Updated weights for policy 0, policy_version 950 (0.0007) +[2023-03-03 11:25:22,684][16994] Fps is (10 sec: 3276.0, 60 sec: 2901.3, 300 sec: 2898.4). Total num frames: 979968. Throughput: 0: 2974.6. Samples: 972736. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:25:22,688][16994] Avg episode reward: [(0, '29.464')] +[2023-03-03 11:25:23,718][17031] Updated weights for policy 0, policy_version 960 (0.0010) +[2023-03-03 11:25:27,144][17031] Updated weights for policy 0, policy_version 970 (0.0008) +[2023-03-03 11:25:27,684][16994] Fps is (10 sec: 3072.0, 60 sec: 2935.4, 300 sec: 2891.5). Total num frames: 994304. Throughput: 0: 3039.9. Samples: 990355. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:25:27,691][16994] Avg episode reward: [(0, '26.950')] +[2023-03-03 11:25:30,482][17031] Updated weights for policy 0, policy_version 980 (0.0007) +[2023-03-03 11:25:32,684][16994] Fps is (10 sec: 2969.7, 60 sec: 2969.5, 300 sec: 2888.0). Total num frames: 1009664. Throughput: 0: 3038.2. Samples: 1008497. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:25:32,685][16994] Avg episode reward: [(0, '24.933')] +[2023-03-03 11:25:33,873][17031] Updated weights for policy 0, policy_version 990 (0.0008) +[2023-03-03 11:25:37,336][17031] Updated weights for policy 0, policy_version 1000 (0.0007) +[2023-03-03 11:25:37,683][16994] Fps is (10 sec: 3071.8, 60 sec: 3037.8, 300 sec: 2891.5). Total num frames: 1025024. Throughput: 0: 3025.2. Samples: 1017296. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:25:37,684][16994] Avg episode reward: [(0, '23.356')] +[2023-03-03 11:25:37,688][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001001_1025024.pth... +[2023-03-03 11:25:37,785][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000318_325632.pth +[2023-03-03 11:25:40,543][17031] Updated weights for policy 0, policy_version 1010 (0.0007) +[2023-03-03 11:25:42,680][16994] Fps is (10 sec: 3073.2, 60 sec: 3038.1, 300 sec: 2895.0). Total num frames: 1040384. Throughput: 0: 3050.9. Samples: 1036254. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:25:42,681][16994] Avg episode reward: [(0, '21.580')] +[2023-03-03 11:25:43,708][17031] Updated weights for policy 0, policy_version 1020 (0.0007) +[2023-03-03 11:25:46,853][17031] Updated weights for policy 0, policy_version 1030 (0.0007) +[2023-03-03 11:25:47,681][16994] Fps is (10 sec: 3175.2, 60 sec: 3072.2, 300 sec: 2912.3). Total num frames: 1056768. Throughput: 0: 3106.1. Samples: 1055600. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:25:47,681][16994] Avg episode reward: [(0, '21.689')] +[2023-03-03 11:25:50,305][17031] Updated weights for policy 0, policy_version 1040 (0.0007) +[2023-03-03 11:25:52,683][16994] Fps is (10 sec: 3071.3, 60 sec: 3054.9, 300 sec: 2908.9). Total num frames: 1071104. Throughput: 0: 3115.0. Samples: 1064505. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:25:52,687][16994] Avg episode reward: [(0, '21.957')] +[2023-03-03 11:25:53,894][17031] Updated weights for policy 0, policy_version 1050 (0.0008) +[2023-03-03 11:25:57,684][16994] Fps is (10 sec: 2763.9, 60 sec: 3020.7, 300 sec: 2908.8). Total num frames: 1084416. Throughput: 0: 3062.0. Samples: 1080768. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:25:57,687][16994] Avg episode reward: [(0, '24.141')] +[2023-03-03 11:25:57,993][17031] Updated weights for policy 0, policy_version 1060 (0.0012) +[2023-03-03 11:26:01,546][17031] Updated weights for policy 0, policy_version 1070 (0.0007) +[2023-03-03 11:26:02,681][16994] Fps is (10 sec: 2765.2, 60 sec: 3038.0, 300 sec: 2908.9). Total num frames: 1098752. Throughput: 0: 2994.9. Samples: 1097505. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:02,682][16994] Avg episode reward: [(0, '25.576')] +[2023-03-03 11:26:04,773][17031] Updated weights for policy 0, policy_version 1080 (0.0006) +[2023-03-03 11:26:07,682][16994] Fps is (10 sec: 2970.1, 60 sec: 3037.8, 300 sec: 2908.9). Total num frames: 1114112. Throughput: 0: 2987.5. Samples: 1107167. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:26:07,683][16994] Avg episode reward: [(0, '25.947')] +[2023-03-03 11:26:08,026][17031] Updated weights for policy 0, policy_version 1090 (0.0007) +[2023-03-03 11:26:11,492][17031] Updated weights for policy 0, policy_version 1100 (0.0008) +[2023-03-03 11:26:12,682][16994] Fps is (10 sec: 2969.4, 60 sec: 3020.8, 300 sec: 2908.9). Total num frames: 1128448. Throughput: 0: 3001.8. Samples: 1125435. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:12,685][16994] Avg episode reward: [(0, '25.543')] +[2023-03-03 11:26:15,267][17031] Updated weights for policy 0, policy_version 1110 (0.0007) +[2023-03-03 11:26:17,685][16994] Fps is (10 sec: 2866.4, 60 sec: 2986.5, 300 sec: 2908.8). Total num frames: 1142784. Throughput: 0: 2980.6. Samples: 1142628. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:26:17,687][16994] Avg episode reward: [(0, '26.298')] +[2023-03-03 11:26:18,892][17031] Updated weights for policy 0, policy_version 1120 (0.0007) +[2023-03-03 11:26:22,356][17031] Updated weights for policy 0, policy_version 1130 (0.0007) +[2023-03-03 11:26:22,683][16994] Fps is (10 sec: 2969.3, 60 sec: 2969.7, 300 sec: 2915.8). Total num frames: 1158144. Throughput: 0: 2962.9. Samples: 1150626. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:26:22,685][16994] Avg episode reward: [(0, '26.261')] +[2023-03-03 11:26:25,919][17031] Updated weights for policy 0, policy_version 1140 (0.0007) +[2023-03-03 11:26:27,685][16994] Fps is (10 sec: 2969.7, 60 sec: 2969.5, 300 sec: 2922.7). Total num frames: 1172480. Throughput: 0: 2929.2. Samples: 1168079. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:27,693][16994] Avg episode reward: [(0, '25.393')] +[2023-03-03 11:26:29,464][17031] Updated weights for policy 0, policy_version 1150 (0.0008) +[2023-03-03 11:26:32,683][16994] Fps is (10 sec: 2764.7, 60 sec: 2935.5, 300 sec: 2919.3). Total num frames: 1185792. Throughput: 0: 2869.7. Samples: 1184742. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:32,685][16994] Avg episode reward: [(0, '25.573')] +[2023-03-03 11:26:33,225][17031] Updated weights for policy 0, policy_version 1160 (0.0008) +[2023-03-03 11:26:36,844][17031] Updated weights for policy 0, policy_version 1170 (0.0008) +[2023-03-03 11:26:37,682][16994] Fps is (10 sec: 2765.4, 60 sec: 2918.4, 300 sec: 2926.2). Total num frames: 1200128. Throughput: 0: 2852.0. Samples: 1192844. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:37,684][16994] Avg episode reward: [(0, '23.795')] +[2023-03-03 11:26:40,127][17031] Updated weights for policy 0, policy_version 1180 (0.0007) +[2023-03-03 11:26:42,683][16994] Fps is (10 sec: 2969.4, 60 sec: 2918.2, 300 sec: 2929.7). Total num frames: 1215488. Throughput: 0: 2908.0. Samples: 1211628. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:26:42,685][16994] Avg episode reward: [(0, '26.292')] +[2023-03-03 11:26:43,477][17031] Updated weights for policy 0, policy_version 1190 (0.0008) +[2023-03-03 11:26:46,966][17031] Updated weights for policy 0, policy_version 1200 (0.0007) +[2023-03-03 11:26:47,683][16994] Fps is (10 sec: 2969.4, 60 sec: 2884.1, 300 sec: 2929.7). Total num frames: 1229824. Throughput: 0: 2930.1. Samples: 1229364. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:26:47,686][16994] Avg episode reward: [(0, '26.180')] +[2023-03-03 11:26:50,495][17031] Updated weights for policy 0, policy_version 1210 (0.0007) +[2023-03-03 11:26:52,682][16994] Fps is (10 sec: 2970.0, 60 sec: 2901.3, 300 sec: 2929.7). Total num frames: 1245184. Throughput: 0: 2914.4. Samples: 1238314. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:26:52,684][16994] Avg episode reward: [(0, '27.147')] +[2023-03-03 11:26:54,010][17031] Updated weights for policy 0, policy_version 1220 (0.0007) +[2023-03-03 11:26:57,685][16994] Fps is (10 sec: 2866.7, 60 sec: 2901.3, 300 sec: 2922.7). Total num frames: 1258496. Throughput: 0: 2877.7. Samples: 1254939. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:26:57,687][16994] Avg episode reward: [(0, '26.511')] +[2023-03-03 11:26:57,846][17031] Updated weights for policy 0, policy_version 1230 (0.0008) +[2023-03-03 11:27:01,517][17031] Updated weights for policy 0, policy_version 1240 (0.0008) +[2023-03-03 11:27:02,684][16994] Fps is (10 sec: 2764.4, 60 sec: 2901.2, 300 sec: 2919.3). Total num frames: 1272832. Throughput: 0: 2865.9. Samples: 1271592. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:27:02,685][16994] Avg episode reward: [(0, '26.618')] +[2023-03-03 11:27:05,042][17031] Updated weights for policy 0, policy_version 1250 (0.0008) +[2023-03-03 11:27:07,683][16994] Fps is (10 sec: 2867.8, 60 sec: 2884.2, 300 sec: 2926.2). Total num frames: 1287168. Throughput: 0: 2883.1. Samples: 1280366. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:07,684][16994] Avg episode reward: [(0, '26.821')] +[2023-03-03 11:27:08,349][17031] Updated weights for policy 0, policy_version 1260 (0.0006) +[2023-03-03 11:27:11,975][17031] Updated weights for policy 0, policy_version 1270 (0.0007) +[2023-03-03 11:27:12,682][16994] Fps is (10 sec: 2970.2, 60 sec: 2901.3, 300 sec: 2926.2). Total num frames: 1302528. Throughput: 0: 2890.0. Samples: 1298124. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:12,683][16994] Avg episode reward: [(0, '27.536')] +[2023-03-03 11:27:15,328][17031] Updated weights for policy 0, policy_version 1280 (0.0007) +[2023-03-03 11:27:17,684][16994] Fps is (10 sec: 3071.7, 60 sec: 2918.5, 300 sec: 2926.2). Total num frames: 1317888. Throughput: 0: 2929.7. Samples: 1316578. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:27:17,685][16994] Avg episode reward: [(0, '28.745')] +[2023-03-03 11:27:19,199][17031] Updated weights for policy 0, policy_version 1290 (0.0007) +[2023-03-03 11:27:22,683][16994] Fps is (10 sec: 2764.7, 60 sec: 2867.2, 300 sec: 2922.8). Total num frames: 1330176. Throughput: 0: 2904.9. Samples: 1323565. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:22,686][16994] Avg episode reward: [(0, '28.652')] +[2023-03-03 11:27:22,860][17031] Updated weights for policy 0, policy_version 1300 (0.0007) +[2023-03-03 11:27:26,179][17031] Updated weights for policy 0, policy_version 1310 (0.0008) +[2023-03-03 11:27:27,684][16994] Fps is (10 sec: 2764.6, 60 sec: 2884.3, 300 sec: 2919.3). Total num frames: 1345536. Throughput: 0: 2880.4. Samples: 1341249. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:27,685][16994] Avg episode reward: [(0, '28.455')] +[2023-03-03 11:27:29,291][17031] Updated weights for policy 0, policy_version 1320 (0.0007) +[2023-03-03 11:27:32,384][17031] Updated weights for policy 0, policy_version 1330 (0.0007) +[2023-03-03 11:27:32,680][16994] Fps is (10 sec: 3277.5, 60 sec: 2952.7, 300 sec: 2929.7). Total num frames: 1362944. Throughput: 0: 2927.7. Samples: 1361100. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:27:32,682][16994] Avg episode reward: [(0, '27.391')] +[2023-03-03 11:27:35,647][17031] Updated weights for policy 0, policy_version 1340 (0.0007) +[2023-03-03 11:27:37,684][16994] Fps is (10 sec: 3174.7, 60 sec: 2952.5, 300 sec: 2929.7). Total num frames: 1377280. Throughput: 0: 2943.8. Samples: 1370790. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:37,685][16994] Avg episode reward: [(0, '28.191')] +[2023-03-03 11:27:37,843][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001346_1378304.pth... +[2023-03-03 11:27:37,943][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000000659_674816.pth +[2023-03-03 11:27:39,245][17031] Updated weights for policy 0, policy_version 1350 (0.0007) +[2023-03-03 11:27:42,677][17031] Updated weights for policy 0, policy_version 1360 (0.0006) +[2023-03-03 11:27:42,681][16994] Fps is (10 sec: 2969.4, 60 sec: 2952.7, 300 sec: 2933.2). Total num frames: 1392640. Throughput: 0: 2972.9. Samples: 1388707. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:27:42,682][16994] Avg episode reward: [(0, '27.458')] +[2023-03-03 11:27:45,708][17031] Updated weights for policy 0, policy_version 1370 (0.0006) +[2023-03-03 11:27:47,682][16994] Fps is (10 sec: 3072.6, 60 sec: 2969.7, 300 sec: 2933.2). Total num frames: 1408000. Throughput: 0: 3013.3. Samples: 1407182. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:27:47,682][16994] Avg episode reward: [(0, '31.141')] +[2023-03-03 11:27:49,205][17031] Updated weights for policy 0, policy_version 1380 (0.0007) +[2023-03-03 11:27:52,680][16994] Fps is (10 sec: 2969.8, 60 sec: 2952.6, 300 sec: 2926.2). Total num frames: 1422336. Throughput: 0: 3011.7. Samples: 1415884. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:27:52,681][16994] Avg episode reward: [(0, '30.809')] +[2023-03-03 11:27:52,696][17031] Updated weights for policy 0, policy_version 1390 (0.0008) +[2023-03-03 11:27:56,033][17031] Updated weights for policy 0, policy_version 1400 (0.0007) +[2023-03-03 11:27:57,681][16994] Fps is (10 sec: 2969.6, 60 sec: 2986.8, 300 sec: 2922.8). Total num frames: 1437696. Throughput: 0: 3018.2. Samples: 1433942. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:27:57,683][16994] Avg episode reward: [(0, '33.015')] +[2023-03-03 11:27:59,854][17031] Updated weights for policy 0, policy_version 1410 (0.0008) +[2023-03-03 11:28:02,684][16994] Fps is (10 sec: 2866.1, 60 sec: 2969.6, 300 sec: 2915.8). Total num frames: 1451008. Throughput: 0: 2975.3. Samples: 1450471. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:28:02,687][16994] Avg episode reward: [(0, '38.885')] +[2023-03-03 11:28:03,666][17031] Updated weights for policy 0, policy_version 1420 (0.0008) +[2023-03-03 11:28:07,413][17031] Updated weights for policy 0, policy_version 1430 (0.0008) +[2023-03-03 11:28:07,690][16994] Fps is (10 sec: 2660.7, 60 sec: 2952.3, 300 sec: 2912.3). Total num frames: 1464320. Throughput: 0: 2989.5. Samples: 1458109. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:28:07,701][16994] Avg episode reward: [(0, '50.264')] +[2023-03-03 11:28:10,743][17031] Updated weights for policy 0, policy_version 1440 (0.0007) +[2023-03-03 11:28:12,681][16994] Fps is (10 sec: 2868.2, 60 sec: 2952.6, 300 sec: 2916.0). Total num frames: 1479680. Throughput: 0: 2992.3. Samples: 1475893. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:28:12,682][16994] Avg episode reward: [(0, '50.518')] +[2023-03-03 11:28:14,239][17031] Updated weights for policy 0, policy_version 1450 (0.0007) +[2023-03-03 11:28:17,486][17031] Updated weights for policy 0, policy_version 1460 (0.0008) +[2023-03-03 11:28:17,684][16994] Fps is (10 sec: 3073.3, 60 sec: 2952.5, 300 sec: 2915.8). Total num frames: 1495040. Throughput: 0: 2948.7. Samples: 1493800. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:17,685][16994] Avg episode reward: [(0, '44.278')] +[2023-03-03 11:28:21,119][17031] Updated weights for policy 0, policy_version 1470 (0.0009) +[2023-03-03 11:28:22,685][16994] Fps is (10 sec: 2968.3, 60 sec: 2986.5, 300 sec: 2926.2). Total num frames: 1509376. Throughput: 0: 2925.1. Samples: 1502423. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:22,688][16994] Avg episode reward: [(0, '41.011')] +[2023-03-03 11:28:24,637][17031] Updated weights for policy 0, policy_version 1480 (0.0008) +[2023-03-03 11:28:27,684][16994] Fps is (10 sec: 2764.6, 60 sec: 2952.5, 300 sec: 2929.7). Total num frames: 1522688. Throughput: 0: 2924.3. Samples: 1520311. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:27,686][16994] Avg episode reward: [(0, '41.027')] +[2023-03-03 11:28:28,430][17031] Updated weights for policy 0, policy_version 1490 (0.0007) +[2023-03-03 11:28:32,298][17031] Updated weights for policy 0, policy_version 1500 (0.0008) +[2023-03-03 11:28:32,681][16994] Fps is (10 sec: 2766.0, 60 sec: 2901.3, 300 sec: 2926.2). Total num frames: 1537024. Throughput: 0: 2851.7. Samples: 1535505. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:32,682][16994] Avg episode reward: [(0, '40.781')] +[2023-03-03 11:28:36,012][17031] Updated weights for policy 0, policy_version 1510 (0.0007) +[2023-03-03 11:28:37,681][16994] Fps is (10 sec: 2868.1, 60 sec: 2901.4, 300 sec: 2926.2). Total num frames: 1551360. Throughput: 0: 2844.2. Samples: 1543876. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:37,682][16994] Avg episode reward: [(0, '42.893')] +[2023-03-03 11:28:39,190][17031] Updated weights for policy 0, policy_version 1520 (0.0006) +[2023-03-03 11:28:42,312][17031] Updated weights for policy 0, policy_version 1530 (0.0007) +[2023-03-03 11:28:42,683][16994] Fps is (10 sec: 2969.0, 60 sec: 2901.2, 300 sec: 2936.6). Total num frames: 1566720. Throughput: 0: 2872.9. Samples: 1563228. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:42,684][16994] Avg episode reward: [(0, '35.819')] +[2023-03-03 11:28:45,701][17031] Updated weights for policy 0, policy_version 1540 (0.0007) +[2023-03-03 11:28:47,684][16994] Fps is (10 sec: 3173.6, 60 sec: 2918.3, 300 sec: 2947.0). Total num frames: 1583104. Throughput: 0: 2914.7. Samples: 1581633. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:47,685][16994] Avg episode reward: [(0, '32.136')] +[2023-03-03 11:28:48,839][17031] Updated weights for policy 0, policy_version 1550 (0.0006) +[2023-03-03 11:28:52,614][17031] Updated weights for policy 0, policy_version 1560 (0.0008) +[2023-03-03 11:28:52,684][16994] Fps is (10 sec: 3071.8, 60 sec: 2918.2, 300 sec: 2947.0). Total num frames: 1597440. Throughput: 0: 2954.4. Samples: 1591045. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:52,687][16994] Avg episode reward: [(0, '26.815')] +[2023-03-03 11:28:55,831][17031] Updated weights for policy 0, policy_version 1570 (0.0007) +[2023-03-03 11:28:57,682][16994] Fps is (10 sec: 2867.9, 60 sec: 2901.3, 300 sec: 2940.1). Total num frames: 1611776. Throughput: 0: 2951.6. Samples: 1608718. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:28:57,684][16994] Avg episode reward: [(0, '27.026')] +[2023-03-03 11:29:00,070][17031] Updated weights for policy 0, policy_version 1580 (0.0008) +[2023-03-03 11:29:02,683][16994] Fps is (10 sec: 2764.8, 60 sec: 2901.4, 300 sec: 2936.6). Total num frames: 1625088. Throughput: 0: 2893.0. Samples: 1623983. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:29:02,685][16994] Avg episode reward: [(0, '27.992')] +[2023-03-03 11:29:03,608][17031] Updated weights for policy 0, policy_version 1590 (0.0008) +[2023-03-03 11:29:06,891][17031] Updated weights for policy 0, policy_version 1600 (0.0008) +[2023-03-03 11:29:07,684][16994] Fps is (10 sec: 2866.6, 60 sec: 2935.7, 300 sec: 2936.6). Total num frames: 1640448. Throughput: 0: 2904.8. Samples: 1633136. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:29:07,685][16994] Avg episode reward: [(0, '27.508')] +[2023-03-03 11:29:10,317][17031] Updated weights for policy 0, policy_version 1610 (0.0006) +[2023-03-03 11:29:12,684][16994] Fps is (10 sec: 3071.9, 60 sec: 2935.3, 300 sec: 2933.1). Total num frames: 1655808. Throughput: 0: 2915.0. Samples: 1651484. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:29:12,686][16994] Avg episode reward: [(0, '28.500')] +[2023-03-03 11:29:13,581][17031] Updated weights for policy 0, policy_version 1620 (0.0007) +[2023-03-03 11:29:17,015][17031] Updated weights for policy 0, policy_version 1630 (0.0007) +[2023-03-03 11:29:17,683][16994] Fps is (10 sec: 2969.8, 60 sec: 2918.4, 300 sec: 2929.7). Total num frames: 1670144. Throughput: 0: 2981.3. Samples: 1669669. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:29:17,684][16994] Avg episode reward: [(0, '26.629')] +[2023-03-03 11:29:21,099][17031] Updated weights for policy 0, policy_version 1640 (0.0009) +[2023-03-03 11:29:22,683][16994] Fps is (10 sec: 2764.9, 60 sec: 2901.4, 300 sec: 2933.1). Total num frames: 1683456. Throughput: 0: 2954.3. Samples: 1676827. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:29:22,686][16994] Avg episode reward: [(0, '25.562')] +[2023-03-03 11:29:24,513][17031] Updated weights for policy 0, policy_version 1650 (0.0007) +[2023-03-03 11:29:27,683][16994] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2940.1). Total num frames: 1698816. Throughput: 0: 2919.1. Samples: 1694587. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:29:27,683][16994] Avg episode reward: [(0, '24.832')] +[2023-03-03 11:29:27,787][17031] Updated weights for policy 0, policy_version 1660 (0.0007) +[2023-03-03 11:29:31,098][17031] Updated weights for policy 0, policy_version 1670 (0.0007) +[2023-03-03 11:29:32,682][16994] Fps is (10 sec: 3174.6, 60 sec: 2969.5, 300 sec: 2957.5). Total num frames: 1715200. Throughput: 0: 2933.9. Samples: 1713654. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:29:32,684][16994] Avg episode reward: [(0, '24.230')] +[2023-03-03 11:29:34,319][17031] Updated weights for policy 0, policy_version 1680 (0.0006) +[2023-03-03 11:29:37,551][17031] Updated weights for policy 0, policy_version 1690 (0.0007) +[2023-03-03 11:29:37,682][16994] Fps is (10 sec: 3174.7, 60 sec: 2986.6, 300 sec: 2957.5). Total num frames: 1730560. Throughput: 0: 2934.9. Samples: 1723113. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:29:37,682][16994] Avg episode reward: [(0, '22.712')] +[2023-03-03 11:29:37,848][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001691_1731584.pth... +[2023-03-03 11:29:37,925][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001001_1025024.pth +[2023-03-03 11:29:40,724][17031] Updated weights for policy 0, policy_version 1700 (0.0006) +[2023-03-03 11:29:42,681][16994] Fps is (10 sec: 3174.9, 60 sec: 3003.8, 300 sec: 2964.4). Total num frames: 1746944. Throughput: 0: 2964.8. Samples: 1742132. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:29:42,681][16994] Avg episode reward: [(0, '33.891')] +[2023-03-03 11:29:43,965][17031] Updated weights for policy 0, policy_version 1710 (0.0007) +[2023-03-03 11:29:47,154][17031] Updated weights for policy 0, policy_version 1720 (0.0007) +[2023-03-03 11:29:47,684][16994] Fps is (10 sec: 3173.7, 60 sec: 2986.7, 300 sec: 2964.4). Total num frames: 1762304. Throughput: 0: 3049.4. Samples: 1761207. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:29:47,686][16994] Avg episode reward: [(0, '35.401')] +[2023-03-03 11:29:50,291][17031] Updated weights for policy 0, policy_version 1730 (0.0007) +[2023-03-03 11:29:52,684][16994] Fps is (10 sec: 3071.1, 60 sec: 3003.7, 300 sec: 2964.4). Total num frames: 1777664. Throughput: 0: 3063.1. Samples: 1770973. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:29:52,685][16994] Avg episode reward: [(0, '43.094')] +[2023-03-03 11:29:53,638][17031] Updated weights for policy 0, policy_version 1740 (0.0007) +[2023-03-03 11:29:56,850][17031] Updated weights for policy 0, policy_version 1750 (0.0007) +[2023-03-03 11:29:57,683][16994] Fps is (10 sec: 3174.6, 60 sec: 3037.8, 300 sec: 2974.8). Total num frames: 1794048. Throughput: 0: 3070.8. Samples: 1789670. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:29:57,684][16994] Avg episode reward: [(0, '28.493')] +[2023-03-03 11:30:00,060][17031] Updated weights for policy 0, policy_version 1760 (0.0007) +[2023-03-03 11:30:02,684][16994] Fps is (10 sec: 3276.7, 60 sec: 3089.0, 300 sec: 2978.3). Total num frames: 1810432. Throughput: 0: 3095.1. Samples: 1808953. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:02,686][16994] Avg episode reward: [(0, '29.215')] +[2023-03-03 11:30:03,293][17031] Updated weights for policy 0, policy_version 1770 (0.0006) +[2023-03-03 11:30:07,087][17031] Updated weights for policy 0, policy_version 1780 (0.0008) +[2023-03-03 11:30:07,683][16994] Fps is (10 sec: 2969.6, 60 sec: 3055.0, 300 sec: 2971.3). Total num frames: 1823744. Throughput: 0: 3130.3. Samples: 1817691. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:30:07,685][16994] Avg episode reward: [(0, '23.380')] +[2023-03-03 11:30:10,616][17031] Updated weights for policy 0, policy_version 1790 (0.0008) +[2023-03-03 11:30:12,684][16994] Fps is (10 sec: 2867.1, 60 sec: 3054.9, 300 sec: 2967.8). Total num frames: 1839104. Throughput: 0: 3110.6. Samples: 1834569. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:12,686][16994] Avg episode reward: [(0, '30.477')] +[2023-03-03 11:30:14,127][17031] Updated weights for policy 0, policy_version 1800 (0.0009) +[2023-03-03 11:30:17,487][17031] Updated weights for policy 0, policy_version 1810 (0.0007) +[2023-03-03 11:30:17,685][16994] Fps is (10 sec: 2969.2, 60 sec: 3054.8, 300 sec: 2960.9). Total num frames: 1853440. Throughput: 0: 3078.5. Samples: 1852192. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:30:17,686][16994] Avg episode reward: [(0, '33.906')] +[2023-03-03 11:30:20,963][17031] Updated weights for policy 0, policy_version 1820 (0.0008) +[2023-03-03 11:30:22,684][16994] Fps is (10 sec: 2867.3, 60 sec: 3071.9, 300 sec: 2960.9). Total num frames: 1867776. Throughput: 0: 3076.0. Samples: 1861539. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:30:22,685][16994] Avg episode reward: [(0, '38.144')] +[2023-03-03 11:30:24,624][17031] Updated weights for policy 0, policy_version 1830 (0.0008) +[2023-03-03 11:30:27,681][16994] Fps is (10 sec: 2868.1, 60 sec: 3055.0, 300 sec: 2957.5). Total num frames: 1882112. Throughput: 0: 3028.8. Samples: 1878432. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:27,682][16994] Avg episode reward: [(0, '32.024')] +[2023-03-03 11:30:28,129][17031] Updated weights for policy 0, policy_version 1840 (0.0007) +[2023-03-03 11:30:31,670][17031] Updated weights for policy 0, policy_version 1850 (0.0010) +[2023-03-03 11:30:32,683][16994] Fps is (10 sec: 2867.7, 60 sec: 3020.8, 300 sec: 2954.0). Total num frames: 1896448. Throughput: 0: 2992.6. Samples: 1895870. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:32,685][16994] Avg episode reward: [(0, '29.187')] +[2023-03-03 11:30:35,411][17031] Updated weights for policy 0, policy_version 1860 (0.0008) +[2023-03-03 11:30:37,692][16994] Fps is (10 sec: 2864.1, 60 sec: 3003.2, 300 sec: 2950.4). Total num frames: 1910784. Throughput: 0: 2956.7. Samples: 1904050. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:37,696][16994] Avg episode reward: [(0, '21.782')] +[2023-03-03 11:30:39,215][17031] Updated weights for policy 0, policy_version 1870 (0.0008) +[2023-03-03 11:30:42,438][17031] Updated weights for policy 0, policy_version 1880 (0.0006) +[2023-03-03 11:30:42,682][16994] Fps is (10 sec: 2867.2, 60 sec: 2969.5, 300 sec: 2943.5). Total num frames: 1925120. Throughput: 0: 2917.4. Samples: 1920950. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:42,683][16994] Avg episode reward: [(0, '21.178')] +[2023-03-03 11:30:45,660][17031] Updated weights for policy 0, policy_version 1890 (0.0007) +[2023-03-03 11:30:47,683][16994] Fps is (10 sec: 2972.3, 60 sec: 2969.6, 300 sec: 2947.0). Total num frames: 1940480. Throughput: 0: 2901.5. Samples: 1939519. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:47,684][16994] Avg episode reward: [(0, '16.938')] +[2023-03-03 11:30:49,156][17031] Updated weights for policy 0, policy_version 1900 (0.0007) +[2023-03-03 11:30:52,683][16994] Fps is (10 sec: 2969.4, 60 sec: 2952.6, 300 sec: 2950.5). Total num frames: 1954816. Throughput: 0: 2905.4. Samples: 1948432. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:52,684][16994] Avg episode reward: [(0, '18.879')] +[2023-03-03 11:30:52,687][17031] Updated weights for policy 0, policy_version 1910 (0.0007) +[2023-03-03 11:30:56,121][17031] Updated weights for policy 0, policy_version 1920 (0.0007) +[2023-03-03 11:30:57,682][16994] Fps is (10 sec: 2969.9, 60 sec: 2935.5, 300 sec: 2954.0). Total num frames: 1970176. Throughput: 0: 2924.8. Samples: 1966178. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:30:57,683][16994] Avg episode reward: [(0, '21.724')] +[2023-03-03 11:30:59,453][17031] Updated weights for policy 0, policy_version 1930 (0.0007) +[2023-03-03 11:31:02,681][16994] Fps is (10 sec: 3072.7, 60 sec: 2918.5, 300 sec: 2954.0). Total num frames: 1985536. Throughput: 0: 2934.2. Samples: 1984222. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:31:02,682][16994] Avg episode reward: [(0, '33.330')] +[2023-03-03 11:31:02,987][17031] Updated weights for policy 0, policy_version 1940 (0.0007) +[2023-03-03 11:31:06,354][17031] Updated weights for policy 0, policy_version 1950 (0.0007) +[2023-03-03 11:31:07,682][16994] Fps is (10 sec: 3072.0, 60 sec: 2952.6, 300 sec: 2957.4). Total num frames: 2000896. Throughput: 0: 2922.2. Samples: 1993031. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:07,683][16994] Avg episode reward: [(0, '36.803')] +[2023-03-03 11:31:09,642][17031] Updated weights for policy 0, policy_version 1960 (0.0007) +[2023-03-03 11:31:12,682][16994] Fps is (10 sec: 3071.6, 60 sec: 2952.6, 300 sec: 2960.9). Total num frames: 2016256. Throughput: 0: 2957.6. Samples: 2011526. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:31:12,683][16994] Avg episode reward: [(0, '39.234')] +[2023-03-03 11:31:13,041][17031] Updated weights for policy 0, policy_version 1970 (0.0007) +[2023-03-03 11:31:16,297][17031] Updated weights for policy 0, policy_version 1980 (0.0007) +[2023-03-03 11:31:17,683][16994] Fps is (10 sec: 2969.3, 60 sec: 2952.6, 300 sec: 2957.4). Total num frames: 2030592. Throughput: 0: 2985.1. Samples: 2030203. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:17,684][16994] Avg episode reward: [(0, '29.976')] +[2023-03-03 11:31:19,785][17031] Updated weights for policy 0, policy_version 1990 (0.0007) +[2023-03-03 11:31:22,682][16994] Fps is (10 sec: 2969.6, 60 sec: 2969.7, 300 sec: 2960.9). Total num frames: 2045952. Throughput: 0: 2998.3. Samples: 2038945. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:22,685][16994] Avg episode reward: [(0, '29.448')] +[2023-03-03 11:31:23,168][17031] Updated weights for policy 0, policy_version 2000 (0.0008) +[2023-03-03 11:31:26,555][17031] Updated weights for policy 0, policy_version 2010 (0.0008) +[2023-03-03 11:31:27,684][16994] Fps is (10 sec: 3071.7, 60 sec: 2986.5, 300 sec: 2967.9). Total num frames: 2061312. Throughput: 0: 3024.7. Samples: 2057067. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:31:27,685][16994] Avg episode reward: [(0, '27.317')] +[2023-03-03 11:31:29,915][17031] Updated weights for policy 0, policy_version 2020 (0.0007) +[2023-03-03 11:31:32,683][16994] Fps is (10 sec: 3071.8, 60 sec: 3003.7, 300 sec: 2971.3). Total num frames: 2076672. Throughput: 0: 3021.4. Samples: 2075484. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) +[2023-03-03 11:31:32,683][16994] Avg episode reward: [(0, '24.669')] +[2023-03-03 11:31:33,231][17031] Updated weights for policy 0, policy_version 2030 (0.0014) +[2023-03-03 11:31:36,495][17031] Updated weights for policy 0, policy_version 2040 (0.0007) +[2023-03-03 11:31:37,684][16994] Fps is (10 sec: 3072.0, 60 sec: 3021.2, 300 sec: 2971.3). Total num frames: 2092032. Throughput: 0: 3030.1. Samples: 2084789. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:37,685][16994] Avg episode reward: [(0, '22.335')] +[2023-03-03 11:31:37,831][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002044_2093056.pth... +[2023-03-03 11:31:37,915][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001346_1378304.pth +[2023-03-03 11:31:39,691][17031] Updated weights for policy 0, policy_version 2050 (0.0007) +[2023-03-03 11:31:42,684][16994] Fps is (10 sec: 3174.2, 60 sec: 3054.9, 300 sec: 2978.3). Total num frames: 2108416. Throughput: 0: 3056.5. Samples: 2103725. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:42,684][16994] Avg episode reward: [(0, '21.471')] +[2023-03-03 11:31:42,939][17031] Updated weights for policy 0, policy_version 2060 (0.0006) +[2023-03-03 11:31:46,491][17031] Updated weights for policy 0, policy_version 2070 (0.0007) +[2023-03-03 11:31:47,683][16994] Fps is (10 sec: 3072.2, 60 sec: 3037.9, 300 sec: 2974.8). Total num frames: 2122752. Throughput: 0: 3053.3. Samples: 2121627. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:31:47,684][16994] Avg episode reward: [(0, '21.633')] +[2023-03-03 11:31:50,155][17031] Updated weights for policy 0, policy_version 2080 (0.0008) +[2023-03-03 11:31:52,684][16994] Fps is (10 sec: 2764.7, 60 sec: 3020.8, 300 sec: 2974.8). Total num frames: 2136064. Throughput: 0: 3041.7. Samples: 2129916. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:31:52,686][16994] Avg episode reward: [(0, '26.563')] +[2023-03-03 11:31:53,777][17031] Updated weights for policy 0, policy_version 2090 (0.0007) +[2023-03-03 11:31:57,684][16994] Fps is (10 sec: 2662.2, 60 sec: 2986.6, 300 sec: 2971.3). Total num frames: 2149376. Throughput: 0: 3005.1. Samples: 2146759. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-03-03 11:31:57,685][16994] Avg episode reward: [(0, '27.451')] +[2023-03-03 11:31:57,828][17031] Updated weights for policy 0, policy_version 2100 (0.0008) +[2023-03-03 11:32:01,430][17031] Updated weights for policy 0, policy_version 2110 (0.0012) +[2023-03-03 11:32:02,685][16994] Fps is (10 sec: 2764.5, 60 sec: 2969.4, 300 sec: 2971.3). Total num frames: 2163712. Throughput: 0: 2939.2. Samples: 2162473. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:32:02,687][16994] Avg episode reward: [(0, '26.785')] +[2023-03-03 11:32:04,804][17031] Updated weights for policy 0, policy_version 2120 (0.0007) +[2023-03-03 11:32:07,681][16994] Fps is (10 sec: 3073.0, 60 sec: 2986.7, 300 sec: 2974.8). Total num frames: 2180096. Throughput: 0: 2953.5. Samples: 2171847. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:07,681][16994] Avg episode reward: [(0, '24.261')] +[2023-03-03 11:32:07,947][17031] Updated weights for policy 0, policy_version 2130 (0.0007) +[2023-03-03 11:32:11,117][17031] Updated weights for policy 0, policy_version 2140 (0.0007) +[2023-03-03 11:32:12,684][16994] Fps is (10 sec: 3277.3, 60 sec: 3003.7, 300 sec: 2978.3). Total num frames: 2196480. Throughput: 0: 2986.6. Samples: 2191461. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:32:12,684][16994] Avg episode reward: [(0, '20.585')] +[2023-03-03 11:32:14,130][17031] Updated weights for policy 0, policy_version 2150 (0.0007) +[2023-03-03 11:32:17,187][17031] Updated weights for policy 0, policy_version 2160 (0.0007) +[2023-03-03 11:32:17,685][16994] Fps is (10 sec: 3275.5, 60 sec: 3037.8, 300 sec: 2992.1). Total num frames: 2212864. Throughput: 0: 3029.0. Samples: 2211796. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:17,685][16994] Avg episode reward: [(0, '23.611')] +[2023-03-03 11:32:20,395][17031] Updated weights for policy 0, policy_version 2170 (0.0007) +[2023-03-03 11:32:22,684][16994] Fps is (10 sec: 3276.8, 60 sec: 3054.9, 300 sec: 2995.6). Total num frames: 2229248. Throughput: 0: 3030.3. Samples: 2221153. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:32:22,685][16994] Avg episode reward: [(0, '28.913')] +[2023-03-03 11:32:23,491][17031] Updated weights for policy 0, policy_version 2180 (0.0007) +[2023-03-03 11:32:26,598][17031] Updated weights for policy 0, policy_version 2190 (0.0007) +[2023-03-03 11:32:27,681][16994] Fps is (10 sec: 3278.0, 60 sec: 3072.2, 300 sec: 2992.2). Total num frames: 2245632. Throughput: 0: 3059.6. Samples: 2241401. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:32:27,681][16994] Avg episode reward: [(0, '36.480')] +[2023-03-03 11:32:29,700][17031] Updated weights for policy 0, policy_version 2200 (0.0007) +[2023-03-03 11:32:32,684][16994] Fps is (10 sec: 3276.7, 60 sec: 3089.0, 300 sec: 2999.1). Total num frames: 2262016. Throughput: 0: 3097.7. Samples: 2261024. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:32,685][16994] Avg episode reward: [(0, '34.381')] +[2023-03-03 11:32:32,704][17031] Updated weights for policy 0, policy_version 2210 (0.0006) +[2023-03-03 11:32:35,869][17031] Updated weights for policy 0, policy_version 2220 (0.0007) +[2023-03-03 11:32:37,684][16994] Fps is (10 sec: 3275.8, 60 sec: 3106.1, 300 sec: 3002.5). Total num frames: 2278400. Throughput: 0: 3130.5. Samples: 2270789. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:32:37,685][16994] Avg episode reward: [(0, '30.567')] +[2023-03-03 11:32:38,857][17031] Updated weights for policy 0, policy_version 2230 (0.0006) +[2023-03-03 11:32:41,867][17031] Updated weights for policy 0, policy_version 2240 (0.0006) +[2023-03-03 11:32:42,682][16994] Fps is (10 sec: 3379.8, 60 sec: 3123.3, 300 sec: 3009.5). Total num frames: 2295808. Throughput: 0: 3209.0. Samples: 2291160. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:42,683][16994] Avg episode reward: [(0, '35.577')] +[2023-03-03 11:32:44,906][17031] Updated weights for policy 0, policy_version 2250 (0.0006) +[2023-03-03 11:32:47,680][16994] Fps is (10 sec: 3483.0, 60 sec: 3174.6, 300 sec: 3019.9). Total num frames: 2313216. Throughput: 0: 3315.6. Samples: 2311658. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:47,681][16994] Avg episode reward: [(0, '42.404')] +[2023-03-03 11:32:47,952][17031] Updated weights for policy 0, policy_version 2260 (0.0006) +[2023-03-03 11:32:50,958][17031] Updated weights for policy 0, policy_version 2270 (0.0006) +[2023-03-03 11:32:52,683][16994] Fps is (10 sec: 3378.8, 60 sec: 3225.6, 300 sec: 3023.4). Total num frames: 2329600. Throughput: 0: 3334.5. Samples: 2321906. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:32:52,685][16994] Avg episode reward: [(0, '44.664')] +[2023-03-03 11:32:53,952][17031] Updated weights for policy 0, policy_version 2280 (0.0006) +[2023-03-03 11:32:56,997][17031] Updated weights for policy 0, policy_version 2290 (0.0006) +[2023-03-03 11:32:57,682][16994] Fps is (10 sec: 3378.6, 60 sec: 3294.0, 300 sec: 3037.3). Total num frames: 2347008. Throughput: 0: 3342.8. Samples: 2341882. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:32:57,683][16994] Avg episode reward: [(0, '52.804')] +[2023-03-03 11:33:00,038][17031] Updated weights for policy 0, policy_version 2300 (0.0007) +[2023-03-03 11:33:02,684][16994] Fps is (10 sec: 3379.1, 60 sec: 3328.1, 300 sec: 3047.7). Total num frames: 2363392. Throughput: 0: 3341.4. Samples: 2362157. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:33:02,684][16994] Avg episode reward: [(0, '47.901')] +[2023-03-03 11:33:03,050][17031] Updated weights for policy 0, policy_version 2310 (0.0006) +[2023-03-03 11:33:06,115][17031] Updated weights for policy 0, policy_version 2320 (0.0007) +[2023-03-03 11:33:07,684][16994] Fps is (10 sec: 3378.6, 60 sec: 3344.9, 300 sec: 3054.6). Total num frames: 2380800. Throughput: 0: 3359.9. Samples: 2372347. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:33:07,684][16994] Avg episode reward: [(0, '45.054')] +[2023-03-03 11:33:09,214][17031] Updated weights for policy 0, policy_version 2330 (0.0006) +[2023-03-03 11:33:12,214][17031] Updated weights for policy 0, policy_version 2340 (0.0006) +[2023-03-03 11:33:12,681][16994] Fps is (10 sec: 3380.2, 60 sec: 3345.2, 300 sec: 3058.1). Total num frames: 2397184. Throughput: 0: 3361.8. Samples: 2392682. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:33:12,681][16994] Avg episode reward: [(0, '26.640')] +[2023-03-03 11:33:15,310][17031] Updated weights for policy 0, policy_version 2350 (0.0007) +[2023-03-03 11:33:17,685][16994] Fps is (10 sec: 3174.2, 60 sec: 3328.0, 300 sec: 3061.6). Total num frames: 2412544. Throughput: 0: 3357.8. Samples: 2412128. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:33:17,686][16994] Avg episode reward: [(0, '23.482')] +[2023-03-03 11:33:18,826][17031] Updated weights for policy 0, policy_version 2360 (0.0007) +[2023-03-03 11:33:22,445][17031] Updated weights for policy 0, policy_version 2370 (0.0009) +[2023-03-03 11:33:22,684][16994] Fps is (10 sec: 2968.6, 60 sec: 3293.8, 300 sec: 3065.1). Total num frames: 2426880. Throughput: 0: 3324.3. Samples: 2420382. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:33:22,685][16994] Avg episode reward: [(0, '26.256')] +[2023-03-03 11:33:25,630][17031] Updated weights for policy 0, policy_version 2380 (0.0006) +[2023-03-03 11:33:27,684][16994] Fps is (10 sec: 3072.1, 60 sec: 3293.7, 300 sec: 3072.0). Total num frames: 2443264. Throughput: 0: 3283.0. Samples: 2438899. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:33:27,685][16994] Avg episode reward: [(0, '26.117')] +[2023-03-03 11:33:28,897][17031] Updated weights for policy 0, policy_version 2390 (0.0007) +[2023-03-03 11:33:32,437][17031] Updated weights for policy 0, policy_version 2400 (0.0007) +[2023-03-03 11:33:32,683][16994] Fps is (10 sec: 3072.4, 60 sec: 3259.8, 300 sec: 3072.0). Total num frames: 2457600. Throughput: 0: 3226.0. Samples: 2456836. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) +[2023-03-03 11:33:32,684][16994] Avg episode reward: [(0, '31.739')] +[2023-03-03 11:33:35,962][17031] Updated weights for policy 0, policy_version 2410 (0.0007) +[2023-03-03 11:33:37,685][16994] Fps is (10 sec: 2866.9, 60 sec: 3225.6, 300 sec: 3068.5). Total num frames: 2471936. Throughput: 0: 3190.1. Samples: 2465467. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:33:37,686][16994] Avg episode reward: [(0, '29.308')] +[2023-03-03 11:33:37,755][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002415_2472960.pth... +[2023-03-03 11:33:37,830][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000001691_1731584.pth +[2023-03-03 11:33:39,378][17031] Updated weights for policy 0, policy_version 2420 (0.0008) +[2023-03-03 11:33:42,594][17031] Updated weights for policy 0, policy_version 2430 (0.0007) +[2023-03-03 11:33:42,680][16994] Fps is (10 sec: 3072.9, 60 sec: 3208.7, 300 sec: 3068.6). Total num frames: 2488320. Throughput: 0: 3162.3. Samples: 2484180. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:33:42,680][16994] Avg episode reward: [(0, '33.102')] +[2023-03-03 11:33:45,841][17031] Updated weights for policy 0, policy_version 2440 (0.0008) +[2023-03-03 11:33:47,683][16994] Fps is (10 sec: 3175.1, 60 sec: 3174.2, 300 sec: 3072.0). Total num frames: 2503680. Throughput: 0: 3130.8. Samples: 2503042. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:33:47,683][16994] Avg episode reward: [(0, '31.296')] +[2023-03-03 11:33:48,869][17031] Updated weights for policy 0, policy_version 2450 (0.0006) +[2023-03-03 11:33:52,082][17031] Updated weights for policy 0, policy_version 2460 (0.0007) +[2023-03-03 11:33:52,684][16994] Fps is (10 sec: 3173.3, 60 sec: 3174.4, 300 sec: 3078.9). Total num frames: 2520064. Throughput: 0: 3118.0. Samples: 2512658. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:33:52,685][16994] Avg episode reward: [(0, '32.047')] +[2023-03-03 11:33:55,386][17031] Updated weights for policy 0, policy_version 2470 (0.0006) +[2023-03-03 11:33:57,683][16994] Fps is (10 sec: 3276.9, 60 sec: 3157.3, 300 sec: 3089.4). Total num frames: 2536448. Throughput: 0: 3093.9. Samples: 2531914. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:33:57,683][16994] Avg episode reward: [(0, '27.344')] +[2023-03-03 11:33:58,432][17031] Updated weights for policy 0, policy_version 2480 (0.0006) +[2023-03-03 11:34:01,465][17031] Updated weights for policy 0, policy_version 2490 (0.0007) +[2023-03-03 11:34:02,684][16994] Fps is (10 sec: 3379.0, 60 sec: 3174.4, 300 sec: 3096.3). Total num frames: 2553856. Throughput: 0: 3110.3. Samples: 2552091. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:02,684][16994] Avg episode reward: [(0, '24.376')] +[2023-03-03 11:34:04,531][17031] Updated weights for policy 0, policy_version 2500 (0.0007) +[2023-03-03 11:34:07,684][16994] Fps is (10 sec: 3276.4, 60 sec: 3140.2, 300 sec: 3096.3). Total num frames: 2569216. Throughput: 0: 3147.4. Samples: 2562016. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:34:07,685][16994] Avg episode reward: [(0, '22.074')] +[2023-03-03 11:34:07,710][17031] Updated weights for policy 0, policy_version 2510 (0.0008) +[2023-03-03 11:34:11,112][17031] Updated weights for policy 0, policy_version 2520 (0.0009) +[2023-03-03 11:34:12,685][16994] Fps is (10 sec: 3071.7, 60 sec: 3123.0, 300 sec: 3099.7). Total num frames: 2584576. Throughput: 0: 3148.6. Samples: 2580589. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:12,687][16994] Avg episode reward: [(0, '24.059')] +[2023-03-03 11:34:14,603][17031] Updated weights for policy 0, policy_version 2530 (0.0006) +[2023-03-03 11:34:17,683][16994] Fps is (10 sec: 3072.1, 60 sec: 3123.2, 300 sec: 3106.7). Total num frames: 2599936. Throughput: 0: 3151.8. Samples: 2598670. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:17,684][16994] Avg episode reward: [(0, '23.265')] +[2023-03-03 11:34:17,778][17031] Updated weights for policy 0, policy_version 2540 (0.0008) +[2023-03-03 11:34:20,789][17031] Updated weights for policy 0, policy_version 2550 (0.0006) +[2023-03-03 11:34:22,682][16994] Fps is (10 sec: 3175.4, 60 sec: 3157.4, 300 sec: 3110.2). Total num frames: 2616320. Throughput: 0: 3186.3. Samples: 2608842. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:22,683][16994] Avg episode reward: [(0, '24.341')] +[2023-03-03 11:34:23,855][17031] Updated weights for policy 0, policy_version 2560 (0.0007) +[2023-03-03 11:34:27,090][17031] Updated weights for policy 0, policy_version 2570 (0.0006) +[2023-03-03 11:34:27,684][16994] Fps is (10 sec: 3276.7, 60 sec: 3157.3, 300 sec: 3110.2). Total num frames: 2632704. Throughput: 0: 3206.5. Samples: 2628484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:34:27,684][16994] Avg episode reward: [(0, '22.922')] +[2023-03-03 11:34:30,220][17031] Updated weights for policy 0, policy_version 2580 (0.0008) +[2023-03-03 11:34:32,683][16994] Fps is (10 sec: 3378.8, 60 sec: 3208.5, 300 sec: 3117.1). Total num frames: 2650112. Throughput: 0: 3232.5. Samples: 2648503. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:34:32,684][16994] Avg episode reward: [(0, '23.665')] +[2023-03-03 11:34:33,271][17031] Updated weights for policy 0, policy_version 2590 (0.0007) +[2023-03-03 11:34:36,515][17031] Updated weights for policy 0, policy_version 2600 (0.0007) +[2023-03-03 11:34:37,681][16994] Fps is (10 sec: 3277.7, 60 sec: 3225.8, 300 sec: 3113.7). Total num frames: 2665472. Throughput: 0: 3244.7. Samples: 2658661. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:34:37,682][16994] Avg episode reward: [(0, '21.654')] +[2023-03-03 11:34:39,973][17031] Updated weights for policy 0, policy_version 2610 (0.0006) +[2023-03-03 11:34:42,681][16994] Fps is (10 sec: 2970.2, 60 sec: 3191.4, 300 sec: 3110.2). Total num frames: 2679808. Throughput: 0: 3181.5. Samples: 2675076. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-03-03 11:34:42,683][16994] Avg episode reward: [(0, '22.080')] +[2023-03-03 11:34:43,588][17031] Updated weights for policy 0, policy_version 2620 (0.0009) +[2023-03-03 11:34:46,725][17031] Updated weights for policy 0, policy_version 2630 (0.0007) +[2023-03-03 11:34:47,683][16994] Fps is (10 sec: 3071.3, 60 sec: 3208.5, 300 sec: 3113.7). Total num frames: 2696192. Throughput: 0: 3166.7. Samples: 2694590. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:47,684][16994] Avg episode reward: [(0, '23.732')] +[2023-03-03 11:34:49,751][17031] Updated weights for policy 0, policy_version 2640 (0.0007) +[2023-03-03 11:34:52,683][16994] Fps is (10 sec: 3276.0, 60 sec: 3208.5, 300 sec: 3113.7). Total num frames: 2712576. Throughput: 0: 3169.7. Samples: 2704653. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:52,684][16994] Avg episode reward: [(0, '26.436')] +[2023-03-03 11:34:52,822][17031] Updated weights for policy 0, policy_version 2650 (0.0006) +[2023-03-03 11:34:55,859][17031] Updated weights for policy 0, policy_version 2660 (0.0006) +[2023-03-03 11:34:57,681][16994] Fps is (10 sec: 3277.6, 60 sec: 3208.6, 300 sec: 3113.7). Total num frames: 2728960. Throughput: 0: 3204.6. Samples: 2724783. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:34:57,681][16994] Avg episode reward: [(0, '26.730')] +[2023-03-03 11:34:58,889][17031] Updated weights for policy 0, policy_version 2670 (0.0007) +[2023-03-03 11:35:01,922][17031] Updated weights for policy 0, policy_version 2680 (0.0006) +[2023-03-03 11:35:02,683][16994] Fps is (10 sec: 3379.3, 60 sec: 3208.6, 300 sec: 3127.5). Total num frames: 2746368. Throughput: 0: 3253.1. Samples: 2745058. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2023-03-03 11:35:02,684][16994] Avg episode reward: [(0, '25.389')] +[2023-03-03 11:35:04,973][17031] Updated weights for policy 0, policy_version 2690 (0.0007) +[2023-03-03 11:35:07,683][16994] Fps is (10 sec: 3276.0, 60 sec: 3208.6, 300 sec: 3127.6). Total num frames: 2761728. Throughput: 0: 3250.6. Samples: 2755125. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:35:07,684][16994] Avg episode reward: [(0, '23.020')] +[2023-03-03 11:35:08,645][17031] Updated weights for policy 0, policy_version 2700 (0.0007) +[2023-03-03 11:35:11,945][17031] Updated weights for policy 0, policy_version 2710 (0.0007) +[2023-03-03 11:35:12,681][16994] Fps is (10 sec: 3072.7, 60 sec: 3208.8, 300 sec: 3131.1). Total num frames: 2777088. Throughput: 0: 3201.6. Samples: 2772544. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:35:12,681][16994] Avg episode reward: [(0, '23.368')] +[2023-03-03 11:35:15,370][17031] Updated weights for policy 0, policy_version 2720 (0.0008) +[2023-03-03 11:35:17,682][16994] Fps is (10 sec: 2969.9, 60 sec: 3191.5, 300 sec: 3131.0). Total num frames: 2791424. Throughput: 0: 3157.8. Samples: 2790602. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:35:17,684][16994] Avg episode reward: [(0, '26.126')] +[2023-03-03 11:35:18,877][17031] Updated weights for policy 0, policy_version 2730 (0.0008) +[2023-03-03 11:35:22,233][17031] Updated weights for policy 0, policy_version 2740 (0.0007) +[2023-03-03 11:35:22,680][16994] Fps is (10 sec: 2969.7, 60 sec: 3174.5, 300 sec: 3134.5). Total num frames: 2806784. Throughput: 0: 3132.4. Samples: 2799615. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:35:22,681][16994] Avg episode reward: [(0, '31.719')] +[2023-03-03 11:35:25,359][17031] Updated weights for policy 0, policy_version 2750 (0.0006) +[2023-03-03 11:35:27,680][16994] Fps is (10 sec: 3175.1, 60 sec: 3174.6, 300 sec: 3141.4). Total num frames: 2823168. Throughput: 0: 3189.9. Samples: 2818617. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:35:27,681][16994] Avg episode reward: [(0, '35.354')] +[2023-03-03 11:35:28,514][17031] Updated weights for policy 0, policy_version 2760 (0.0007) +[2023-03-03 11:35:31,757][17031] Updated weights for policy 0, policy_version 2770 (0.0006) +[2023-03-03 11:35:32,681][16994] Fps is (10 sec: 3174.2, 60 sec: 3140.4, 300 sec: 3145.0). Total num frames: 2838528. Throughput: 0: 3180.6. Samples: 2837712. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2023-03-03 11:35:32,683][16994] Avg episode reward: [(0, '33.391')] +[2023-03-03 11:35:35,204][17031] Updated weights for policy 0, policy_version 2780 (0.0008) +[2023-03-03 11:35:37,684][16994] Fps is (10 sec: 2968.5, 60 sec: 3123.1, 300 sec: 3144.9). Total num frames: 2852864. Throughput: 0: 3151.4. Samples: 2846466. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-03-03 11:35:37,688][16994] Avg episode reward: [(0, '28.531')] +[2023-03-03 11:35:37,694][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002787_2853888.pth... +[2023-03-03 11:35:37,788][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002044_2093056.pth +[2023-03-03 11:35:38,865][17031] Updated weights for policy 0, policy_version 2790 (0.0009) +[2023-03-03 11:35:42,421][17031] Updated weights for policy 0, policy_version 2800 (0.0008) +[2023-03-03 11:35:42,685][16994] Fps is (10 sec: 2866.4, 60 sec: 3123.1, 300 sec: 3141.4). Total num frames: 2867200. Throughput: 0: 3074.9. Samples: 2863164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-03-03 11:35:42,692][16994] Avg episode reward: [(0, '26.635')] +[2023-03-03 11:35:44,767][16994] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 16994], exiting... +[2023-03-03 11:35:44,776][16994] Runner profile tree view: +main_loop: 965.0570 +[2023-03-03 11:35:44,779][16994] Collected {0: 2873344}, FPS: 2977.4 +[2023-03-03 11:35:44,770][17030] Stopping Batcher_0... +[2023-03-03 11:35:44,781][17030] Loop batcher_evt_loop terminating... +[2023-03-03 11:35:44,784][17030] Saving /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002806_2873344.pth... +[2023-03-03 11:35:44,774][17036] Stopping RolloutWorker_w5... +[2023-03-03 11:35:44,776][17035] Stopping RolloutWorker_w3... +[2023-03-03 11:35:44,787][17036] Loop rollout_proc5_evt_loop terminating... +[2023-03-03 11:35:44,789][17035] Loop rollout_proc3_evt_loop terminating... +[2023-03-03 11:35:44,774][17033] Stopping RolloutWorker_w1... +[2023-03-03 11:35:44,777][17034] Stopping RolloutWorker_w2... +[2023-03-03 11:35:44,791][17033] Loop rollout_proc1_evt_loop terminating... +[2023-03-03 11:35:44,792][17034] Loop rollout_proc2_evt_loop terminating... +[2023-03-03 11:35:44,774][17037] Stopping RolloutWorker_w4... +[2023-03-03 11:35:44,780][17038] Stopping RolloutWorker_w6... +[2023-03-03 11:35:44,794][17038] Loop rollout_proc6_evt_loop terminating... +[2023-03-03 11:35:44,794][17037] Loop rollout_proc4_evt_loop terminating... +[2023-03-03 11:35:44,790][17032] Stopping RolloutWorker_w0... +[2023-03-03 11:35:44,789][17039] Stopping RolloutWorker_w7... +[2023-03-03 11:35:44,802][17032] Loop rollout_proc0_evt_loop terminating... +[2023-03-03 11:35:44,805][17039] Loop rollout_proc7_evt_loop terminating... +[2023-03-03 11:35:44,917][17030] Removing /Users/quentingallouedec/gia/data/envs/metaworld/train_dir/pick-place-v2/checkpoint_p0/checkpoint_000002415_2472960.pth +[2023-03-03 11:35:44,958][17030] Stopping LearnerWorker_p0... +[2023-03-03 11:35:44,958][17030] Loop learner_proc0_evt_loop terminating... +[2023-03-03 11:35:45,199][17031] Weights refcount: 2 0 +[2023-03-03 11:35:45,205][17031] Stopping InferenceWorker_p0-w0... +[2023-03-03 11:35:45,206][17031] Loop inference_proc0-0_evt_loop terminating...