[2023-02-24 07:11:05,490][00276] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-24 07:11:05,494][00276] Rollout worker 0 uses device cpu [2023-02-24 07:11:05,499][00276] Rollout worker 1 uses device cpu [2023-02-24 07:11:05,500][00276] Rollout worker 2 uses device cpu [2023-02-24 07:11:05,503][00276] Rollout worker 3 uses device cpu [2023-02-24 07:11:05,505][00276] Rollout worker 4 uses device cpu [2023-02-24 07:11:05,506][00276] Rollout worker 5 uses device cpu [2023-02-24 07:11:05,508][00276] Rollout worker 6 uses device cpu [2023-02-24 07:11:05,509][00276] Rollout worker 7 uses device cpu [2023-02-24 07:11:05,731][00276] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-24 07:11:05,736][00276] InferenceWorker_p0-w0: min num requests: 2 [2023-02-24 07:11:05,776][00276] Starting all processes... [2023-02-24 07:11:05,781][00276] Starting process learner_proc0 [2023-02-24 07:11:05,857][00276] Starting all processes... [2023-02-24 07:11:05,869][00276] Starting process inference_proc0-0 [2023-02-24 07:11:05,869][00276] Starting process rollout_proc0 [2023-02-24 07:11:05,869][00276] Starting process rollout_proc1 [2023-02-24 07:11:05,898][00276] Starting process rollout_proc2 [2023-02-24 07:11:05,902][00276] Starting process rollout_proc3 [2023-02-24 07:11:05,902][00276] Starting process rollout_proc4 [2023-02-24 07:11:05,902][00276] Starting process rollout_proc5 [2023-02-24 07:11:05,902][00276] Starting process rollout_proc6 [2023-02-24 07:11:05,902][00276] Starting process rollout_proc7 [2023-02-24 07:11:16,004][11606] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-24 07:11:16,012][11606] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-24 07:11:16,321][11626] Worker 2 uses CPU cores [0] [2023-02-24 07:11:17,104][11627] Worker 3 uses CPU cores [1] [2023-02-24 07:11:17,273][11631] Worker 7 uses CPU cores [1] [2023-02-24 07:11:17,447][11628] Worker 4 uses CPU cores [0] [2023-02-24 07:11:17,450][11622] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-24 07:11:17,460][11630] Worker 6 uses CPU cores [0] [2023-02-24 07:11:17,454][11622] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-24 07:11:17,481][11629] Worker 5 uses CPU cores [1] [2023-02-24 07:11:17,650][11625] Worker 1 uses CPU cores [1] [2023-02-24 07:11:17,677][11623] Worker 0 uses CPU cores [0] [2023-02-24 07:11:18,028][11606] Num visible devices: 1 [2023-02-24 07:11:18,031][11622] Num visible devices: 1 [2023-02-24 07:11:18,052][11606] Starting seed is not provided [2023-02-24 07:11:18,053][11606] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-24 07:11:18,053][11606] Initializing actor-critic model on device cuda:0 [2023-02-24 07:11:18,054][11606] RunningMeanStd input shape: (3, 72, 128) [2023-02-24 07:11:18,056][11606] RunningMeanStd input shape: (1,) [2023-02-24 07:11:18,090][11606] ConvEncoder: input_channels=3 [2023-02-24 07:11:18,606][11606] Conv encoder output size: 512 [2023-02-24 07:11:18,607][11606] Policy head output size: 512 [2023-02-24 07:11:18,736][11606] Created Actor Critic model with architecture: [2023-02-24 07:11:18,737][11606] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): 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=5, bias=True) ) ) [2023-02-24 07:11:25,722][00276] Heartbeat connected on Batcher_0 [2023-02-24 07:11:25,731][00276] Heartbeat connected on InferenceWorker_p0-w0 [2023-02-24 07:11:25,745][00276] Heartbeat connected on RolloutWorker_w0 [2023-02-24 07:11:25,753][00276] Heartbeat connected on RolloutWorker_w2 [2023-02-24 07:11:25,755][00276] Heartbeat connected on RolloutWorker_w1 [2023-02-24 07:11:25,759][00276] Heartbeat connected on RolloutWorker_w3 [2023-02-24 07:11:25,762][00276] Heartbeat connected on RolloutWorker_w4 [2023-02-24 07:11:25,772][00276] Heartbeat connected on RolloutWorker_w6 [2023-02-24 07:11:25,773][00276] Heartbeat connected on RolloutWorker_w5 [2023-02-24 07:11:25,777][00276] Heartbeat connected on RolloutWorker_w7 [2023-02-24 07:11:27,095][11606] Using optimizer [2023-02-24 07:11:27,096][11606] No checkpoints found [2023-02-24 07:11:27,096][11606] Did not load from checkpoint, starting from scratch! [2023-02-24 07:11:27,097][11606] Initialized policy 0 weights for model version 0 [2023-02-24 07:11:27,101][11606] LearnerWorker_p0 finished initialization! [2023-02-24 07:11:27,102][00276] Heartbeat connected on LearnerWorker_p0 [2023-02-24 07:11:27,101][11606] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-24 07:11:27,230][11622] RunningMeanStd input shape: (3, 72, 128) [2023-02-24 07:11:27,231][11622] RunningMeanStd input shape: (1,) [2023-02-24 07:11:27,243][11622] ConvEncoder: input_channels=3 [2023-02-24 07:11:27,341][11622] Conv encoder output size: 512 [2023-02-24 07:11:27,342][11622] Policy head output size: 512 [2023-02-24 07:11:29,593][00276] Inference worker 0-0 is ready! [2023-02-24 07:11:29,595][00276] All inference workers are ready! Signal rollout workers to start! [2023-02-24 07:11:29,716][11626] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,719][11623] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,722][11628] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,736][11631] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,753][11625] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,755][11627] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,759][11630] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:29,775][11629] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:11:30,338][00276] 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) [2023-02-24 07:11:30,968][11631] Decorrelating experience for 0 frames... [2023-02-24 07:11:30,969][11627] Decorrelating experience for 0 frames... [2023-02-24 07:11:30,970][11629] Decorrelating experience for 0 frames... [2023-02-24 07:11:30,971][11623] Decorrelating experience for 0 frames... [2023-02-24 07:11:30,968][11626] Decorrelating experience for 0 frames... [2023-02-24 07:11:30,972][11628] Decorrelating experience for 0 frames... [2023-02-24 07:11:32,177][11628] Decorrelating experience for 32 frames... [2023-02-24 07:11:32,206][11623] Decorrelating experience for 32 frames... [2023-02-24 07:11:32,299][11630] Decorrelating experience for 0 frames... [2023-02-24 07:11:32,706][11627] Decorrelating experience for 32 frames... [2023-02-24 07:11:32,708][11629] Decorrelating experience for 32 frames... [2023-02-24 07:11:32,713][11631] Decorrelating experience for 32 frames... [2023-02-24 07:11:32,728][11625] Decorrelating experience for 0 frames... [2023-02-24 07:11:33,952][11625] Decorrelating experience for 32 frames... [2023-02-24 07:11:34,150][11628] Decorrelating experience for 64 frames... [2023-02-24 07:11:34,158][11623] Decorrelating experience for 64 frames... [2023-02-24 07:11:34,359][11626] Decorrelating experience for 32 frames... [2023-02-24 07:11:34,361][11630] Decorrelating experience for 32 frames... [2023-02-24 07:11:35,338][00276] 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) [2023-02-24 07:11:35,843][11631] Decorrelating experience for 64 frames... [2023-02-24 07:11:36,207][11629] Decorrelating experience for 64 frames... [2023-02-24 07:11:36,249][11625] Decorrelating experience for 64 frames... [2023-02-24 07:11:36,263][11627] Decorrelating experience for 64 frames... [2023-02-24 07:11:36,276][11628] Decorrelating experience for 96 frames... [2023-02-24 07:11:36,347][11623] Decorrelating experience for 96 frames... [2023-02-24 07:11:36,721][11626] Decorrelating experience for 64 frames... [2023-02-24 07:11:37,192][11630] Decorrelating experience for 64 frames... [2023-02-24 07:11:37,785][11631] Decorrelating experience for 96 frames... [2023-02-24 07:11:38,061][11629] Decorrelating experience for 96 frames... [2023-02-24 07:11:38,316][11625] Decorrelating experience for 96 frames... [2023-02-24 07:11:38,727][11630] Decorrelating experience for 96 frames... [2023-02-24 07:11:39,196][11627] Decorrelating experience for 96 frames... [2023-02-24 07:11:39,603][11626] Decorrelating experience for 96 frames... [2023-02-24 07:11:40,338][00276] 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) [2023-02-24 07:11:43,427][11606] Signal inference workers to stop experience collection... [2023-02-24 07:11:43,455][11622] InferenceWorker_p0-w0: stopping experience collection [2023-02-24 07:11:45,338][00276] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 149.3. Samples: 2240. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-24 07:11:45,340][00276] Avg episode reward: [(0, '1.833')] [2023-02-24 07:11:45,794][11606] Signal inference workers to resume experience collection... [2023-02-24 07:11:45,796][11622] InferenceWorker_p0-w0: resuming experience collection [2023-02-24 07:11:50,338][00276] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 165.5. Samples: 3310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:11:50,345][00276] Avg episode reward: [(0, '3.581')] [2023-02-24 07:11:55,341][00276] Fps is (10 sec: 3276.0, 60 sec: 1310.6, 300 sec: 1310.6). Total num frames: 32768. Throughput: 0: 318.1. Samples: 7954. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:11:55,344][00276] Avg episode reward: [(0, '3.868')] [2023-02-24 07:11:57,670][11622] Updated weights for policy 0, policy_version 10 (0.0371) [2023-02-24 07:12:00,338][00276] Fps is (10 sec: 2457.6, 60 sec: 1501.9, 300 sec: 1501.9). Total num frames: 45056. Throughput: 0: 399.0. Samples: 11970. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:12:00,347][00276] Avg episode reward: [(0, '4.405')] [2023-02-24 07:12:05,338][00276] Fps is (10 sec: 3687.3, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 428.0. Samples: 14980. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:12:05,346][00276] Avg episode reward: [(0, '4.563')] [2023-02-24 07:12:07,780][11622] Updated weights for policy 0, policy_version 20 (0.0012) [2023-02-24 07:12:10,338][00276] Fps is (10 sec: 4505.6, 60 sec: 2252.8, 300 sec: 2252.8). Total num frames: 90112. Throughput: 0: 540.6. Samples: 21626. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2023-02-24 07:12:10,340][00276] Avg episode reward: [(0, '4.462')] [2023-02-24 07:12:15,338][00276] Fps is (10 sec: 3276.8, 60 sec: 2275.6, 300 sec: 2275.6). Total num frames: 102400. Throughput: 0: 588.6. Samples: 26488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:12:15,340][00276] Avg episode reward: [(0, '4.346')] [2023-02-24 07:12:15,351][11606] Saving new best policy, reward=4.346! [2023-02-24 07:12:20,340][00276] Fps is (10 sec: 2866.8, 60 sec: 2375.6, 300 sec: 2375.6). Total num frames: 118784. Throughput: 0: 633.6. Samples: 28514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:12:20,342][00276] Avg episode reward: [(0, '4.439')] [2023-02-24 07:12:20,352][11606] Saving new best policy, reward=4.439! [2023-02-24 07:12:21,287][11622] Updated weights for policy 0, policy_version 30 (0.0029) [2023-02-24 07:12:25,338][00276] Fps is (10 sec: 3686.4, 60 sec: 2532.1, 300 sec: 2532.1). Total num frames: 139264. Throughput: 0: 753.2. Samples: 33896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:12:25,344][00276] Avg episode reward: [(0, '4.413')] [2023-02-24 07:12:30,338][00276] Fps is (10 sec: 4096.5, 60 sec: 2662.4, 300 sec: 2662.4). Total num frames: 159744. Throughput: 0: 849.4. Samples: 40462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:12:30,341][00276] Avg episode reward: [(0, '4.356')] [2023-02-24 07:12:30,646][11622] Updated weights for policy 0, policy_version 40 (0.0022) [2023-02-24 07:12:35,338][00276] Fps is (10 sec: 3686.4, 60 sec: 2935.5, 300 sec: 2709.7). Total num frames: 176128. Throughput: 0: 883.6. Samples: 43074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:12:35,341][00276] Avg episode reward: [(0, '4.363')] [2023-02-24 07:12:40,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 2691.7). Total num frames: 188416. Throughput: 0: 873.2. Samples: 47248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:12:40,341][00276] Avg episode reward: [(0, '4.391')] [2023-02-24 07:12:43,768][11622] Updated weights for policy 0, policy_version 50 (0.0042) [2023-02-24 07:12:45,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 208896. Throughput: 0: 906.8. Samples: 52774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:12:45,346][00276] Avg episode reward: [(0, '4.328')] [2023-02-24 07:12:50,340][00276] Fps is (10 sec: 4505.0, 60 sec: 3549.8, 300 sec: 2918.3). Total num frames: 233472. Throughput: 0: 912.1. Samples: 56026. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:12:50,348][00276] Avg episode reward: [(0, '4.394')] [2023-02-24 07:12:53,659][11622] Updated weights for policy 0, policy_version 60 (0.0014) [2023-02-24 07:12:55,339][00276] Fps is (10 sec: 4095.9, 60 sec: 3618.3, 300 sec: 2939.5). Total num frames: 249856. Throughput: 0: 893.7. Samples: 61844. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:12:55,344][00276] Avg episode reward: [(0, '4.525')] [2023-02-24 07:12:55,350][11606] Saving new best policy, reward=4.525! [2023-02-24 07:13:00,339][00276] Fps is (10 sec: 2867.5, 60 sec: 3618.1, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 877.8. Samples: 65988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:13:00,347][00276] Avg episode reward: [(0, '4.547')] [2023-02-24 07:13:00,362][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth... [2023-02-24 07:13:00,519][11606] Saving new best policy, reward=4.547! [2023-02-24 07:13:05,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 2931.9). Total num frames: 278528. Throughput: 0: 880.6. Samples: 68140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:13:05,341][00276] Avg episode reward: [(0, '4.441')] [2023-02-24 07:13:06,329][11622] Updated weights for policy 0, policy_version 70 (0.0016) [2023-02-24 07:13:10,338][00276] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 2990.1). Total num frames: 299008. Throughput: 0: 902.4. Samples: 74504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:13:10,342][00276] Avg episode reward: [(0, '4.559')] [2023-02-24 07:13:10,352][11606] Saving new best policy, reward=4.559! [2023-02-24 07:13:15,339][00276] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3003.7). Total num frames: 315392. Throughput: 0: 872.1. Samples: 79706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:13:15,347][00276] Avg episode reward: [(0, '4.549')] [2023-02-24 07:13:18,820][11622] Updated weights for policy 0, policy_version 80 (0.0012) [2023-02-24 07:13:20,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 857.9. Samples: 81680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:13:20,343][00276] Avg episode reward: [(0, '4.612')] [2023-02-24 07:13:20,371][11606] Saving new best policy, reward=4.612! [2023-02-24 07:13:25,338][00276] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3027.5). Total num frames: 348160. Throughput: 0: 861.0. Samples: 85994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:13:25,341][00276] Avg episode reward: [(0, '4.386')] [2023-02-24 07:13:29,994][11622] Updated weights for policy 0, policy_version 90 (0.0025) [2023-02-24 07:13:30,339][00276] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3072.0). Total num frames: 368640. Throughput: 0: 878.1. Samples: 92290. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:13:30,342][00276] Avg episode reward: [(0, '4.260')] [2023-02-24 07:13:35,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3047.4). Total num frames: 380928. Throughput: 0: 857.4. Samples: 94606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:13:35,346][00276] Avg episode reward: [(0, '4.371')] [2023-02-24 07:13:40,338][00276] Fps is (10 sec: 2048.0, 60 sec: 3345.1, 300 sec: 2993.2). Total num frames: 389120. Throughput: 0: 796.9. Samples: 97704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:13:40,344][00276] Avg episode reward: [(0, '4.361')] [2023-02-24 07:13:45,340][00276] Fps is (10 sec: 2047.6, 60 sec: 3208.4, 300 sec: 2973.4). Total num frames: 401408. Throughput: 0: 778.6. Samples: 101028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:13:45,342][00276] Avg episode reward: [(0, '4.482')] [2023-02-24 07:13:47,203][11622] Updated weights for policy 0, policy_version 100 (0.0028) [2023-02-24 07:13:50,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3013.5). Total num frames: 421888. Throughput: 0: 784.9. Samples: 103460. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:13:50,342][00276] Avg episode reward: [(0, '4.520')] [2023-02-24 07:13:55,338][00276] Fps is (10 sec: 4096.7, 60 sec: 3208.5, 300 sec: 3050.8). Total num frames: 442368. Throughput: 0: 790.3. Samples: 110068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:13:55,341][00276] Avg episode reward: [(0, '4.614')] [2023-02-24 07:13:55,345][11606] Saving new best policy, reward=4.614! [2023-02-24 07:13:56,668][11622] Updated weights for policy 0, policy_version 110 (0.0019) [2023-02-24 07:14:00,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3058.3). Total num frames: 458752. Throughput: 0: 793.8. Samples: 115426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:14:00,346][00276] Avg episode reward: [(0, '4.660')] [2023-02-24 07:14:00,362][11606] Saving new best policy, reward=4.660! [2023-02-24 07:14:05,340][00276] Fps is (10 sec: 3276.1, 60 sec: 3276.7, 300 sec: 3065.4). Total num frames: 475136. Throughput: 0: 793.9. Samples: 117408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:14:05,343][00276] Avg episode reward: [(0, '4.724')] [2023-02-24 07:14:05,351][11606] Saving new best policy, reward=4.724! [2023-02-24 07:14:09,919][11622] Updated weights for policy 0, policy_version 120 (0.0016) [2023-02-24 07:14:10,339][00276] Fps is (10 sec: 3276.7, 60 sec: 3208.5, 300 sec: 3072.0). Total num frames: 491520. Throughput: 0: 801.1. Samples: 122044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:14:10,348][00276] Avg episode reward: [(0, '4.525')] [2023-02-24 07:14:15,338][00276] Fps is (10 sec: 3687.1, 60 sec: 3276.8, 300 sec: 3103.0). Total num frames: 512000. Throughput: 0: 805.5. Samples: 128538. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:14:15,343][00276] Avg episode reward: [(0, '4.580')] [2023-02-24 07:14:20,339][00276] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3108.1). Total num frames: 528384. Throughput: 0: 823.6. Samples: 131668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:14:20,341][00276] Avg episode reward: [(0, '4.566')] [2023-02-24 07:14:20,547][11622] Updated weights for policy 0, policy_version 130 (0.0013) [2023-02-24 07:14:25,339][00276] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3113.0). Total num frames: 544768. Throughput: 0: 846.5. Samples: 135798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:14:25,342][00276] Avg episode reward: [(0, '4.685')] [2023-02-24 07:14:30,338][00276] Fps is (10 sec: 3276.9, 60 sec: 3208.5, 300 sec: 3117.5). Total num frames: 561152. Throughput: 0: 880.2. Samples: 140634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:14:30,345][00276] Avg episode reward: [(0, '4.669')] [2023-02-24 07:14:32,754][11622] Updated weights for policy 0, policy_version 140 (0.0029) [2023-02-24 07:14:35,338][00276] Fps is (10 sec: 3686.5, 60 sec: 3345.1, 300 sec: 3144.0). Total num frames: 581632. Throughput: 0: 894.4. Samples: 143710. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:14:35,341][00276] Avg episode reward: [(0, '4.754')] [2023-02-24 07:14:35,348][11606] Saving new best policy, reward=4.754! [2023-02-24 07:14:40,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3147.5). Total num frames: 598016. Throughput: 0: 879.9. Samples: 149662. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:14:40,340][00276] Avg episode reward: [(0, '4.850')] [2023-02-24 07:14:40,363][11606] Saving new best policy, reward=4.850! [2023-02-24 07:14:45,024][11622] Updated weights for policy 0, policy_version 150 (0.0022) [2023-02-24 07:14:45,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3150.8). Total num frames: 614400. Throughput: 0: 851.5. Samples: 153744. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:14:45,341][00276] Avg episode reward: [(0, '4.831')] [2023-02-24 07:14:50,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3153.9). Total num frames: 630784. Throughput: 0: 853.4. Samples: 155810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:14:50,345][00276] Avg episode reward: [(0, '4.848')] [2023-02-24 07:14:55,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3176.9). Total num frames: 651264. Throughput: 0: 889.0. Samples: 162050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:14:55,344][00276] Avg episode reward: [(0, '4.913')] [2023-02-24 07:14:55,348][11606] Saving new best policy, reward=4.913! [2023-02-24 07:14:55,758][11622] Updated weights for policy 0, policy_version 160 (0.0026) [2023-02-24 07:15:00,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3179.3). Total num frames: 667648. Throughput: 0: 875.2. Samples: 167924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:15:00,350][00276] Avg episode reward: [(0, '5.119')] [2023-02-24 07:15:00,370][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000164_671744.pth... [2023-02-24 07:15:00,523][11606] Saving new best policy, reward=5.119! [2023-02-24 07:15:05,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3181.5). Total num frames: 684032. Throughput: 0: 848.1. Samples: 169832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:15:05,342][00276] Avg episode reward: [(0, '4.893')] [2023-02-24 07:15:09,373][11622] Updated weights for policy 0, policy_version 170 (0.0014) [2023-02-24 07:15:10,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3165.1). Total num frames: 696320. Throughput: 0: 845.3. Samples: 173838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:15:10,348][00276] Avg episode reward: [(0, '4.827')] [2023-02-24 07:15:15,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3204.0). Total num frames: 720896. Throughput: 0: 879.3. Samples: 180202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:15:15,344][00276] Avg episode reward: [(0, '5.047')] [2023-02-24 07:15:19,282][11622] Updated weights for policy 0, policy_version 180 (0.0017) [2023-02-24 07:15:20,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3205.6). Total num frames: 737280. Throughput: 0: 881.6. Samples: 183384. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:15:20,344][00276] Avg episode reward: [(0, '5.041')] [2023-02-24 07:15:25,346][00276] Fps is (10 sec: 3274.4, 60 sec: 3481.2, 300 sec: 3207.0). Total num frames: 753664. Throughput: 0: 846.9. Samples: 187778. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:15:25,348][00276] Avg episode reward: [(0, '5.069')] [2023-02-24 07:15:30,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3208.5). Total num frames: 770048. Throughput: 0: 852.6. Samples: 192110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:15:30,344][00276] Avg episode reward: [(0, '5.141')] [2023-02-24 07:15:30,351][11606] Saving new best policy, reward=5.141! [2023-02-24 07:15:32,569][11622] Updated weights for policy 0, policy_version 190 (0.0035) [2023-02-24 07:15:35,338][00276] Fps is (10 sec: 3279.2, 60 sec: 3413.3, 300 sec: 3209.9). Total num frames: 786432. Throughput: 0: 875.9. Samples: 195224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:15:35,344][00276] Avg episode reward: [(0, '5.182')] [2023-02-24 07:15:35,356][11606] Saving new best policy, reward=5.182! [2023-02-24 07:15:40,339][00276] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3227.6). Total num frames: 806912. Throughput: 0: 881.4. Samples: 201714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:15:40,346][00276] Avg episode reward: [(0, '5.354')] [2023-02-24 07:15:40,357][11606] Saving new best policy, reward=5.354! [2023-02-24 07:15:44,222][11622] Updated weights for policy 0, policy_version 200 (0.0012) [2023-02-24 07:15:45,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3212.5). Total num frames: 819200. Throughput: 0: 839.5. Samples: 205700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:15:45,353][00276] Avg episode reward: [(0, '5.156')] [2023-02-24 07:15:50,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3213.8). Total num frames: 835584. Throughput: 0: 843.5. Samples: 207790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:15:50,346][00276] Avg episode reward: [(0, '5.160')] [2023-02-24 07:15:55,277][11622] Updated weights for policy 0, policy_version 210 (0.0017) [2023-02-24 07:15:55,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3245.9). Total num frames: 860160. Throughput: 0: 886.9. Samples: 213748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:15:55,347][00276] Avg episode reward: [(0, '5.021')] [2023-02-24 07:16:00,339][00276] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3246.5). Total num frames: 876544. Throughput: 0: 888.3. Samples: 220176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:16:00,343][00276] Avg episode reward: [(0, '5.319')] [2023-02-24 07:16:05,342][00276] Fps is (10 sec: 3275.7, 60 sec: 3481.4, 300 sec: 3247.0). Total num frames: 892928. Throughput: 0: 862.4. Samples: 222196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:16:05,345][00276] Avg episode reward: [(0, '5.501')] [2023-02-24 07:16:05,348][11606] Saving new best policy, reward=5.501! [2023-02-24 07:16:07,953][11622] Updated weights for policy 0, policy_version 220 (0.0018) [2023-02-24 07:16:10,338][00276] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3232.9). Total num frames: 905216. Throughput: 0: 856.0. Samples: 226290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:16:10,343][00276] Avg episode reward: [(0, '5.652')] [2023-02-24 07:16:10,357][11606] Saving new best policy, reward=5.652! [2023-02-24 07:16:15,342][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.1, 300 sec: 3248.0). Total num frames: 925696. Throughput: 0: 890.4. Samples: 232182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:16:15,350][00276] Avg episode reward: [(0, '5.453')] [2023-02-24 07:16:18,340][11622] Updated weights for policy 0, policy_version 230 (0.0020) [2023-02-24 07:16:20,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 950272. Throughput: 0: 890.6. Samples: 235302. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:16:20,342][00276] Avg episode reward: [(0, '5.584')] [2023-02-24 07:16:25,338][00276] Fps is (10 sec: 3687.6, 60 sec: 3482.0, 300 sec: 3262.9). Total num frames: 962560. Throughput: 0: 859.0. Samples: 240368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:16:25,341][00276] Avg episode reward: [(0, '5.430')] [2023-02-24 07:16:30,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3304.6). Total num frames: 974848. Throughput: 0: 861.3. Samples: 244458. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:16:30,344][00276] Avg episode reward: [(0, '5.511')] [2023-02-24 07:16:31,591][11622] Updated weights for policy 0, policy_version 240 (0.0020) [2023-02-24 07:16:35,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 995328. Throughput: 0: 879.8. Samples: 247380. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:16:35,341][00276] Avg episode reward: [(0, '5.395')] [2023-02-24 07:16:40,339][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 882.5. Samples: 253462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:16:40,350][00276] Avg episode reward: [(0, '5.347')] [2023-02-24 07:16:42,288][11622] Updated weights for policy 0, policy_version 250 (0.0014) [2023-02-24 07:16:45,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3429.5). Total num frames: 1032192. Throughput: 0: 842.1. Samples: 258072. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:16:45,342][00276] Avg episode reward: [(0, '5.395')] [2023-02-24 07:16:50,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3429.6). Total num frames: 1044480. Throughput: 0: 841.4. Samples: 260054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:16:50,341][00276] Avg episode reward: [(0, '5.703')] [2023-02-24 07:16:50,353][11606] Saving new best policy, reward=5.703! [2023-02-24 07:16:55,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3443.4). Total num frames: 1060864. Throughput: 0: 860.1. Samples: 264994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:16:55,341][00276] Avg episode reward: [(0, '6.216')] [2023-02-24 07:16:55,347][11606] Saving new best policy, reward=6.216! [2023-02-24 07:16:55,614][11622] Updated weights for policy 0, policy_version 260 (0.0015) [2023-02-24 07:17:00,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 1077248. Throughput: 0: 832.0. Samples: 269618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:17:00,344][00276] Avg episode reward: [(0, '6.378')] [2023-02-24 07:17:00,367][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000263_1077248.pth... [2023-02-24 07:17:00,508][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth [2023-02-24 07:17:00,516][11606] Saving new best policy, reward=6.378! [2023-02-24 07:17:05,341][00276] Fps is (10 sec: 2457.0, 60 sec: 3208.6, 300 sec: 3374.0). Total num frames: 1085440. Throughput: 0: 797.9. Samples: 271208. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:17:05,347][00276] Avg episode reward: [(0, '6.298')] [2023-02-24 07:17:10,339][00276] Fps is (10 sec: 2048.0, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 1097728. Throughput: 0: 753.6. Samples: 274282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:17:10,350][00276] Avg episode reward: [(0, '6.394')] [2023-02-24 07:17:10,371][11606] Saving new best policy, reward=6.394! [2023-02-24 07:17:12,969][11622] Updated weights for policy 0, policy_version 270 (0.0016) [2023-02-24 07:17:15,338][00276] Fps is (10 sec: 2458.2, 60 sec: 3072.2, 300 sec: 3360.1). Total num frames: 1110016. Throughput: 0: 748.3. Samples: 278130. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:17:15,345][00276] Avg episode reward: [(0, '6.569')] [2023-02-24 07:17:15,353][11606] Saving new best policy, reward=6.569! [2023-02-24 07:17:20,339][00276] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3360.1). Total num frames: 1130496. Throughput: 0: 748.6. Samples: 281068. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:17:20,343][00276] Avg episode reward: [(0, '6.391')] [2023-02-24 07:17:23,440][11622] Updated weights for policy 0, policy_version 280 (0.0013) [2023-02-24 07:17:25,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 3360.1). Total num frames: 1150976. Throughput: 0: 752.6. Samples: 287330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:17:25,345][00276] Avg episode reward: [(0, '6.246')] [2023-02-24 07:17:30,339][00276] Fps is (10 sec: 3276.7, 60 sec: 3140.3, 300 sec: 3346.2). Total num frames: 1163264. Throughput: 0: 741.9. Samples: 291458. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:17:30,345][00276] Avg episode reward: [(0, '6.305')] [2023-02-24 07:17:35,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3346.2). Total num frames: 1175552. Throughput: 0: 740.3. Samples: 293366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:17:35,346][00276] Avg episode reward: [(0, '6.121')] [2023-02-24 07:17:37,322][11622] Updated weights for policy 0, policy_version 290 (0.0027) [2023-02-24 07:17:40,338][00276] Fps is (10 sec: 3686.5, 60 sec: 3072.0, 300 sec: 3360.1). Total num frames: 1200128. Throughput: 0: 754.0. Samples: 298926. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:17:40,347][00276] Avg episode reward: [(0, '6.553')] [2023-02-24 07:17:45,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3140.3, 300 sec: 3346.2). Total num frames: 1220608. Throughput: 0: 796.0. Samples: 305436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:17:45,342][00276] Avg episode reward: [(0, '6.791')] [2023-02-24 07:17:45,350][11606] Saving new best policy, reward=6.791! [2023-02-24 07:17:48,069][11622] Updated weights for policy 0, policy_version 300 (0.0019) [2023-02-24 07:17:50,340][00276] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 1232896. Throughput: 0: 804.6. Samples: 307412. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:17:50,347][00276] Avg episode reward: [(0, '6.951')] [2023-02-24 07:17:50,363][11606] Saving new best policy, reward=6.951! [2023-02-24 07:17:55,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 3332.3). Total num frames: 1245184. Throughput: 0: 823.6. Samples: 311342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:17:55,344][00276] Avg episode reward: [(0, '6.697')] [2023-02-24 07:18:00,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3346.2). Total num frames: 1265664. Throughput: 0: 864.5. Samples: 317034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:18:00,344][00276] Avg episode reward: [(0, '6.539')] [2023-02-24 07:18:00,533][11622] Updated weights for policy 0, policy_version 310 (0.0031) [2023-02-24 07:18:05,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3345.2, 300 sec: 3346.2). Total num frames: 1286144. Throughput: 0: 868.6. Samples: 320156. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:18:05,344][00276] Avg episode reward: [(0, '6.695')] [2023-02-24 07:18:10,340][00276] Fps is (10 sec: 3276.3, 60 sec: 3345.0, 300 sec: 3332.3). Total num frames: 1298432. Throughput: 0: 836.6. Samples: 324976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:18:10,346][00276] Avg episode reward: [(0, '7.124')] [2023-02-24 07:18:10,361][11606] Saving new best policy, reward=7.124! [2023-02-24 07:18:13,807][11622] Updated weights for policy 0, policy_version 320 (0.0013) [2023-02-24 07:18:15,339][00276] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1314816. Throughput: 0: 831.4. Samples: 328872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:18:15,345][00276] Avg episode reward: [(0, '7.345')] [2023-02-24 07:18:15,354][11606] Saving new best policy, reward=7.345! [2023-02-24 07:18:20,338][00276] Fps is (10 sec: 3277.3, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 1331200. Throughput: 0: 848.3. Samples: 331538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:18:20,340][00276] Avg episode reward: [(0, '7.589')] [2023-02-24 07:18:20,435][11606] Saving new best policy, reward=7.589! [2023-02-24 07:18:24,408][11622] Updated weights for policy 0, policy_version 330 (0.0019) [2023-02-24 07:18:25,338][00276] Fps is (10 sec: 3686.6, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 1351680. Throughput: 0: 860.2. Samples: 337636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:18:25,341][00276] Avg episode reward: [(0, '7.491')] [2023-02-24 07:18:30,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1368064. Throughput: 0: 821.3. Samples: 342396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:18:30,347][00276] Avg episode reward: [(0, '7.516')] [2023-02-24 07:18:35,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1380352. Throughput: 0: 822.1. Samples: 344406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:18:35,343][00276] Avg episode reward: [(0, '7.672')] [2023-02-24 07:18:35,345][11606] Saving new best policy, reward=7.672! [2023-02-24 07:18:38,061][11622] Updated weights for policy 0, policy_version 340 (0.0037) [2023-02-24 07:18:40,339][00276] Fps is (10 sec: 3276.7, 60 sec: 3345.0, 300 sec: 3387.9). Total num frames: 1400832. Throughput: 0: 840.3. Samples: 349158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:18:40,342][00276] Avg episode reward: [(0, '8.000')] [2023-02-24 07:18:40,358][11606] Saving new best policy, reward=8.000! [2023-02-24 07:18:45,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 1421312. Throughput: 0: 848.6. Samples: 355222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:18:45,346][00276] Avg episode reward: [(0, '8.771')] [2023-02-24 07:18:45,350][11606] Saving new best policy, reward=8.771! [2023-02-24 07:18:48,736][11622] Updated weights for policy 0, policy_version 350 (0.0019) [2023-02-24 07:18:50,338][00276] Fps is (10 sec: 3686.5, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1437696. Throughput: 0: 840.8. Samples: 357992. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:18:50,345][00276] Avg episode reward: [(0, '8.863')] [2023-02-24 07:18:50,357][11606] Saving new best policy, reward=8.863! [2023-02-24 07:18:55,339][00276] Fps is (10 sec: 2867.0, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1449984. Throughput: 0: 822.9. Samples: 362006. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:18:55,345][00276] Avg episode reward: [(0, '8.623')] [2023-02-24 07:19:00,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 1466368. Throughput: 0: 843.4. Samples: 366826. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:19:00,343][00276] Avg episode reward: [(0, '8.083')] [2023-02-24 07:19:00,353][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000358_1466368.pth... [2023-02-24 07:19:00,482][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000164_671744.pth [2023-02-24 07:19:02,032][11622] Updated weights for policy 0, policy_version 360 (0.0024) [2023-02-24 07:19:05,338][00276] Fps is (10 sec: 3686.7, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 1486848. Throughput: 0: 850.9. Samples: 369830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:19:05,343][00276] Avg episode reward: [(0, '8.281')] [2023-02-24 07:19:10,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3360.1). Total num frames: 1503232. Throughput: 0: 846.4. Samples: 375724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:19:10,343][00276] Avg episode reward: [(0, '7.956')] [2023-02-24 07:19:14,142][11622] Updated weights for policy 0, policy_version 370 (0.0013) [2023-02-24 07:19:15,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 1515520. Throughput: 0: 830.1. Samples: 379752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:19:15,350][00276] Avg episode reward: [(0, '8.128')] [2023-02-24 07:19:20,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 1531904. Throughput: 0: 829.9. Samples: 381750. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:19:20,343][00276] Avg episode reward: [(0, '8.413')] [2023-02-24 07:19:25,173][11622] Updated weights for policy 0, policy_version 380 (0.0044) [2023-02-24 07:19:25,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1556480. Throughput: 0: 863.0. Samples: 387992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:19:25,344][00276] Avg episode reward: [(0, '8.690')] [2023-02-24 07:19:30,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1572864. Throughput: 0: 855.9. Samples: 393738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:19:30,344][00276] Avg episode reward: [(0, '9.094')] [2023-02-24 07:19:30,357][11606] Saving new best policy, reward=9.094! [2023-02-24 07:19:35,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1585152. Throughput: 0: 836.8. Samples: 395648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:19:35,349][00276] Avg episode reward: [(0, '9.287')] [2023-02-24 07:19:35,351][11606] Saving new best policy, reward=9.287! [2023-02-24 07:19:38,981][11622] Updated weights for policy 0, policy_version 390 (0.0018) [2023-02-24 07:19:40,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 1601536. Throughput: 0: 836.9. Samples: 399668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:19:40,340][00276] Avg episode reward: [(0, '9.166')] [2023-02-24 07:19:45,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 1622016. Throughput: 0: 874.0. Samples: 406156. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:19:45,343][00276] Avg episode reward: [(0, '9.224')] [2023-02-24 07:19:48,574][11622] Updated weights for policy 0, policy_version 400 (0.0022) [2023-02-24 07:19:50,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1642496. Throughput: 0: 877.8. Samples: 409332. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:19:50,343][00276] Avg episode reward: [(0, '10.032')] [2023-02-24 07:19:50,359][11606] Saving new best policy, reward=10.032! [2023-02-24 07:19:55,344][00276] Fps is (10 sec: 3275.0, 60 sec: 3413.1, 300 sec: 3346.2). Total num frames: 1654784. Throughput: 0: 841.3. Samples: 413586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:19:55,349][00276] Avg episode reward: [(0, '10.159')] [2023-02-24 07:19:55,354][11606] Saving new best policy, reward=10.159! [2023-02-24 07:20:00,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1671168. Throughput: 0: 841.5. Samples: 417620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:20:00,346][00276] Avg episode reward: [(0, '10.222')] [2023-02-24 07:20:00,356][11606] Saving new best policy, reward=10.222! [2023-02-24 07:20:02,291][11622] Updated weights for policy 0, policy_version 410 (0.0026) [2023-02-24 07:20:05,338][00276] Fps is (10 sec: 3688.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1691648. Throughput: 0: 866.8. Samples: 420754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:20:05,346][00276] Avg episode reward: [(0, '10.935')] [2023-02-24 07:20:05,349][11606] Saving new best policy, reward=10.935! [2023-02-24 07:20:10,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1708032. Throughput: 0: 867.9. Samples: 427048. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:20:10,343][00276] Avg episode reward: [(0, '10.888')] [2023-02-24 07:20:13,436][11622] Updated weights for policy 0, policy_version 420 (0.0016) [2023-02-24 07:20:15,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 1724416. Throughput: 0: 835.9. Samples: 431354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:20:15,342][00276] Avg episode reward: [(0, '11.392')] [2023-02-24 07:20:15,346][11606] Saving new best policy, reward=11.392! [2023-02-24 07:20:20,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3332.4). Total num frames: 1736704. Throughput: 0: 837.7. Samples: 433344. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:20:20,345][00276] Avg episode reward: [(0, '12.001')] [2023-02-24 07:20:20,358][11606] Saving new best policy, reward=12.001! [2023-02-24 07:20:25,341][00276] Fps is (10 sec: 2866.5, 60 sec: 3276.7, 300 sec: 3332.3). Total num frames: 1753088. Throughput: 0: 856.4. Samples: 438210. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:20:25,344][00276] Avg episode reward: [(0, '12.729')] [2023-02-24 07:20:25,350][11606] Saving new best policy, reward=12.729! [2023-02-24 07:20:27,750][11622] Updated weights for policy 0, policy_version 430 (0.0044) [2023-02-24 07:20:30,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 1765376. Throughput: 0: 799.8. Samples: 442146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:20:30,341][00276] Avg episode reward: [(0, '12.096')] [2023-02-24 07:20:35,338][00276] Fps is (10 sec: 2458.2, 60 sec: 3208.5, 300 sec: 3290.7). Total num frames: 1777664. Throughput: 0: 765.2. Samples: 443764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:20:35,342][00276] Avg episode reward: [(0, '11.760')] [2023-02-24 07:20:40,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 3290.7). Total num frames: 1789952. Throughput: 0: 756.0. Samples: 447600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:20:40,341][00276] Avg episode reward: [(0, '11.820')] [2023-02-24 07:20:43,159][11622] Updated weights for policy 0, policy_version 440 (0.0016) [2023-02-24 07:20:45,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 1810432. Throughput: 0: 781.0. Samples: 452766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:20:45,347][00276] Avg episode reward: [(0, '12.557')] [2023-02-24 07:20:50,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 3290.7). Total num frames: 1830912. Throughput: 0: 782.0. Samples: 455944. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:20:50,341][00276] Avg episode reward: [(0, '13.746')] [2023-02-24 07:20:50,350][11606] Saving new best policy, reward=13.746! [2023-02-24 07:20:52,867][11622] Updated weights for policy 0, policy_version 450 (0.0013) [2023-02-24 07:20:55,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3208.8, 300 sec: 3290.7). Total num frames: 1847296. Throughput: 0: 770.4. Samples: 461714. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:20:55,341][00276] Avg episode reward: [(0, '14.367')] [2023-02-24 07:20:55,351][11606] Saving new best policy, reward=14.367! [2023-02-24 07:21:00,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3276.8). Total num frames: 1859584. Throughput: 0: 764.1. Samples: 465740. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:21:00,346][00276] Avg episode reward: [(0, '16.055')] [2023-02-24 07:21:00,363][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000454_1859584.pth... [2023-02-24 07:21:00,531][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000263_1077248.pth [2023-02-24 07:21:00,547][11606] Saving new best policy, reward=16.055! [2023-02-24 07:21:05,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 1880064. Throughput: 0: 763.4. Samples: 467696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:05,344][00276] Avg episode reward: [(0, '16.832')] [2023-02-24 07:21:05,350][11606] Saving new best policy, reward=16.832! [2023-02-24 07:21:06,276][11622] Updated weights for policy 0, policy_version 460 (0.0037) [2023-02-24 07:21:10,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 1900544. Throughput: 0: 795.4. Samples: 474000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:10,342][00276] Avg episode reward: [(0, '16.738')] [2023-02-24 07:21:15,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 3276.8). Total num frames: 1916928. Throughput: 0: 832.0. Samples: 479586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:21:15,342][00276] Avg episode reward: [(0, '16.955')] [2023-02-24 07:21:15,346][11606] Saving new best policy, reward=16.955! [2023-02-24 07:21:17,952][11622] Updated weights for policy 0, policy_version 470 (0.0013) [2023-02-24 07:21:20,346][00276] Fps is (10 sec: 2865.1, 60 sec: 3208.1, 300 sec: 3276.7). Total num frames: 1929216. Throughput: 0: 840.4. Samples: 481588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:21:20,348][00276] Avg episode reward: [(0, '16.680')] [2023-02-24 07:21:25,339][00276] Fps is (10 sec: 2867.1, 60 sec: 3208.6, 300 sec: 3290.7). Total num frames: 1945600. Throughput: 0: 848.4. Samples: 485780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:21:25,345][00276] Avg episode reward: [(0, '17.041')] [2023-02-24 07:21:25,350][11606] Saving new best policy, reward=17.041! [2023-02-24 07:21:29,610][11622] Updated weights for policy 0, policy_version 480 (0.0018) [2023-02-24 07:21:30,338][00276] Fps is (10 sec: 3689.1, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 1966080. Throughput: 0: 873.1. Samples: 492054. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:30,347][00276] Avg episode reward: [(0, '16.074')] [2023-02-24 07:21:35,342][00276] Fps is (10 sec: 4094.7, 60 sec: 3481.4, 300 sec: 3290.6). Total num frames: 1986560. Throughput: 0: 875.1. Samples: 495328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:35,352][00276] Avg episode reward: [(0, '16.711')] [2023-02-24 07:21:40,344][00276] Fps is (10 sec: 3275.0, 60 sec: 3481.3, 300 sec: 3276.7). Total num frames: 1998848. Throughput: 0: 843.5. Samples: 499678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:40,355][00276] Avg episode reward: [(0, '16.628')] [2023-02-24 07:21:42,674][11622] Updated weights for policy 0, policy_version 490 (0.0019) [2023-02-24 07:21:45,338][00276] Fps is (10 sec: 2868.2, 60 sec: 3413.3, 300 sec: 3290.7). Total num frames: 2015232. Throughput: 0: 849.2. Samples: 503956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:21:45,344][00276] Avg episode reward: [(0, '17.311')] [2023-02-24 07:21:45,348][11606] Saving new best policy, reward=17.311! [2023-02-24 07:21:50,338][00276] Fps is (10 sec: 3688.4, 60 sec: 3413.3, 300 sec: 3304.6). Total num frames: 2035712. Throughput: 0: 877.3. Samples: 507176. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-02-24 07:21:50,346][00276] Avg episode reward: [(0, '17.893')] [2023-02-24 07:21:50,357][11606] Saving new best policy, reward=17.893! [2023-02-24 07:21:52,834][11622] Updated weights for policy 0, policy_version 500 (0.0012) [2023-02-24 07:21:55,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 2056192. Throughput: 0: 879.9. Samples: 513594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:21:55,343][00276] Avg episode reward: [(0, '18.796')] [2023-02-24 07:21:55,350][11606] Saving new best policy, reward=18.796! [2023-02-24 07:22:00,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3332.4). Total num frames: 2068480. Throughput: 0: 843.9. Samples: 517562. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:22:00,345][00276] Avg episode reward: [(0, '18.627')] [2023-02-24 07:22:05,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2080768. Throughput: 0: 841.6. Samples: 519456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:22:05,347][00276] Avg episode reward: [(0, '18.587')] [2023-02-24 07:22:06,613][11622] Updated weights for policy 0, policy_version 510 (0.0017) [2023-02-24 07:22:10,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2101248. Throughput: 0: 873.8. Samples: 525100. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:22:10,341][00276] Avg episode reward: [(0, '17.882')] [2023-02-24 07:22:15,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 2125824. Throughput: 0: 878.5. Samples: 531586. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:22:15,343][00276] Avg episode reward: [(0, '16.812')] [2023-02-24 07:22:16,880][11622] Updated weights for policy 0, policy_version 520 (0.0016) [2023-02-24 07:22:20,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3482.0, 300 sec: 3346.2). Total num frames: 2138112. Throughput: 0: 851.7. Samples: 533652. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:22:20,346][00276] Avg episode reward: [(0, '16.691')] [2023-02-24 07:22:25,339][00276] Fps is (10 sec: 2457.5, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2150400. Throughput: 0: 846.2. Samples: 537752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:22:25,347][00276] Avg episode reward: [(0, '15.850')] [2023-02-24 07:22:29,373][11622] Updated weights for policy 0, policy_version 530 (0.0035) [2023-02-24 07:22:30,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2170880. Throughput: 0: 878.7. Samples: 543496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:22:30,344][00276] Avg episode reward: [(0, '15.925')] [2023-02-24 07:22:35,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.5, 300 sec: 3360.1). Total num frames: 2191360. Throughput: 0: 874.6. Samples: 546534. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:22:35,344][00276] Avg episode reward: [(0, '16.316')] [2023-02-24 07:22:40,342][00276] Fps is (10 sec: 3685.1, 60 sec: 3481.7, 300 sec: 3346.2). Total num frames: 2207744. Throughput: 0: 845.4. Samples: 551642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:22:40,345][00276] Avg episode reward: [(0, '16.576')] [2023-02-24 07:22:41,366][11622] Updated weights for policy 0, policy_version 540 (0.0023) [2023-02-24 07:22:45,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2220032. Throughput: 0: 847.5. Samples: 555698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:22:45,348][00276] Avg episode reward: [(0, '18.581')] [2023-02-24 07:22:50,338][00276] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2240512. Throughput: 0: 862.4. Samples: 558262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:22:50,341][00276] Avg episode reward: [(0, '19.029')] [2023-02-24 07:22:50,353][11606] Saving new best policy, reward=19.029! [2023-02-24 07:22:52,876][11622] Updated weights for policy 0, policy_version 550 (0.0020) [2023-02-24 07:22:55,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2260992. Throughput: 0: 874.0. Samples: 564432. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:22:55,344][00276] Avg episode reward: [(0, '19.258')] [2023-02-24 07:22:55,347][11606] Saving new best policy, reward=19.258! [2023-02-24 07:23:00,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2277376. Throughput: 0: 842.0. Samples: 569476. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:23:00,345][00276] Avg episode reward: [(0, '19.877')] [2023-02-24 07:23:00,359][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000556_2277376.pth... [2023-02-24 07:23:00,531][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000358_1466368.pth [2023-02-24 07:23:00,545][11606] Saving new best policy, reward=19.877! [2023-02-24 07:23:05,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2289664. Throughput: 0: 837.6. Samples: 571346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:23:05,346][00276] Avg episode reward: [(0, '20.119')] [2023-02-24 07:23:05,350][11606] Saving new best policy, reward=20.119! [2023-02-24 07:23:06,944][11622] Updated weights for policy 0, policy_version 560 (0.0031) [2023-02-24 07:23:10,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 2306048. Throughput: 0: 847.5. Samples: 575888. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:23:10,342][00276] Avg episode reward: [(0, '17.620')] [2023-02-24 07:23:15,339][00276] Fps is (10 sec: 3686.3, 60 sec: 3345.0, 300 sec: 3374.0). Total num frames: 2326528. Throughput: 0: 857.4. Samples: 582078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:23:15,341][00276] Avg episode reward: [(0, '16.596')] [2023-02-24 07:23:16,689][11622] Updated weights for policy 0, policy_version 570 (0.0013) [2023-02-24 07:23:20,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 2342912. Throughput: 0: 852.9. Samples: 584914. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:23:20,341][00276] Avg episode reward: [(0, '16.505')] [2023-02-24 07:23:25,338][00276] Fps is (10 sec: 2867.3, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2355200. Throughput: 0: 826.5. Samples: 588830. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:23:25,347][00276] Avg episode reward: [(0, '16.625')] [2023-02-24 07:23:30,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2371584. Throughput: 0: 838.7. Samples: 593440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:23:30,341][00276] Avg episode reward: [(0, '16.450')] [2023-02-24 07:23:30,734][11622] Updated weights for policy 0, policy_version 580 (0.0014) [2023-02-24 07:23:35,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2392064. Throughput: 0: 849.7. Samples: 596498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:23:35,341][00276] Avg episode reward: [(0, '18.096')] [2023-02-24 07:23:40,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3345.3, 300 sec: 3346.2). Total num frames: 2408448. Throughput: 0: 841.7. Samples: 602308. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:23:40,346][00276] Avg episode reward: [(0, '20.132')] [2023-02-24 07:23:40,380][11606] Saving new best policy, reward=20.132! [2023-02-24 07:23:42,566][11622] Updated weights for policy 0, policy_version 590 (0.0015) [2023-02-24 07:23:45,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2420736. Throughput: 0: 814.7. Samples: 606138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:23:45,346][00276] Avg episode reward: [(0, '20.909')] [2023-02-24 07:23:45,348][11606] Saving new best policy, reward=20.909! [2023-02-24 07:23:50,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3346.2). Total num frames: 2437120. Throughput: 0: 815.5. Samples: 608044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:23:50,347][00276] Avg episode reward: [(0, '20.625')] [2023-02-24 07:23:55,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 2453504. Throughput: 0: 824.0. Samples: 612966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:23:55,342][00276] Avg episode reward: [(0, '21.042')] [2023-02-24 07:23:55,351][11606] Saving new best policy, reward=21.042! [2023-02-24 07:23:56,590][11622] Updated weights for policy 0, policy_version 600 (0.0026) [2023-02-24 07:24:00,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 2465792. Throughput: 0: 770.7. Samples: 616758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:24:00,343][00276] Avg episode reward: [(0, '22.004')] [2023-02-24 07:24:00,363][11606] Saving new best policy, reward=22.004! [2023-02-24 07:24:05,340][00276] Fps is (10 sec: 2047.7, 60 sec: 3071.9, 300 sec: 3290.7). Total num frames: 2473984. Throughput: 0: 741.5. Samples: 618284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:24:05,346][00276] Avg episode reward: [(0, '22.447')] [2023-02-24 07:24:05,356][11606] Saving new best policy, reward=22.447! [2023-02-24 07:24:10,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 3304.6). Total num frames: 2490368. Throughput: 0: 742.9. Samples: 622262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:24:10,346][00276] Avg episode reward: [(0, '21.554')] [2023-02-24 07:24:11,868][11622] Updated weights for policy 0, policy_version 610 (0.0034) [2023-02-24 07:24:15,338][00276] Fps is (10 sec: 3686.9, 60 sec: 3072.0, 300 sec: 3318.5). Total num frames: 2510848. Throughput: 0: 773.1. Samples: 628230. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:24:15,347][00276] Avg episode reward: [(0, '20.206')] [2023-02-24 07:24:20,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 2531328. Throughput: 0: 779.1. Samples: 631556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:24:20,349][00276] Avg episode reward: [(0, '20.510')] [2023-02-24 07:24:22,033][11622] Updated weights for policy 0, policy_version 620 (0.0016) [2023-02-24 07:24:25,339][00276] Fps is (10 sec: 3686.3, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 2547712. Throughput: 0: 759.6. Samples: 636488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:24:25,344][00276] Avg episode reward: [(0, '20.590')] [2023-02-24 07:24:30,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 2560000. Throughput: 0: 762.8. Samples: 640464. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:24:30,347][00276] Avg episode reward: [(0, '20.275')] [2023-02-24 07:24:34,791][11622] Updated weights for policy 0, policy_version 630 (0.0017) [2023-02-24 07:24:35,338][00276] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 2580480. Throughput: 0: 783.2. Samples: 643288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:24:35,341][00276] Avg episode reward: [(0, '20.319')] [2023-02-24 07:24:40,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 2600960. Throughput: 0: 817.7. Samples: 649762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:24:40,341][00276] Avg episode reward: [(0, '20.133')] [2023-02-24 07:24:45,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 2617344. Throughput: 0: 840.2. Samples: 654566. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:24:45,342][00276] Avg episode reward: [(0, '20.365')] [2023-02-24 07:24:46,481][11622] Updated weights for policy 0, policy_version 640 (0.0022) [2023-02-24 07:24:50,339][00276] Fps is (10 sec: 2867.0, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 2629632. Throughput: 0: 852.8. Samples: 656660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:24:50,344][00276] Avg episode reward: [(0, '20.034')] [2023-02-24 07:24:55,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3318.5). Total num frames: 2650112. Throughput: 0: 878.8. Samples: 661810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:24:55,341][00276] Avg episode reward: [(0, '20.703')] [2023-02-24 07:24:57,942][11622] Updated weights for policy 0, policy_version 650 (0.0025) [2023-02-24 07:25:00,338][00276] Fps is (10 sec: 4096.3, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2670592. Throughput: 0: 885.9. Samples: 668094. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:25:00,340][00276] Avg episode reward: [(0, '18.502')] [2023-02-24 07:25:00,356][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000652_2670592.pth... [2023-02-24 07:25:00,490][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000454_1859584.pth [2023-02-24 07:25:05,339][00276] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3318.5). Total num frames: 2686976. Throughput: 0: 868.3. Samples: 670630. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:25:05,342][00276] Avg episode reward: [(0, '17.937')] [2023-02-24 07:25:10,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3304.6). Total num frames: 2699264. Throughput: 0: 850.8. Samples: 674772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:25:10,347][00276] Avg episode reward: [(0, '18.676')] [2023-02-24 07:25:11,084][11622] Updated weights for policy 0, policy_version 660 (0.0022) [2023-02-24 07:25:15,338][00276] Fps is (10 sec: 2867.3, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2715648. Throughput: 0: 873.2. Samples: 679758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:25:15,347][00276] Avg episode reward: [(0, '19.066')] [2023-02-24 07:25:20,339][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 2740224. Throughput: 0: 880.0. Samples: 682888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:25:20,348][00276] Avg episode reward: [(0, '18.447')] [2023-02-24 07:25:21,129][11622] Updated weights for policy 0, policy_version 670 (0.0023) [2023-02-24 07:25:25,338][00276] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2756608. Throughput: 0: 865.4. Samples: 688706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:25:25,341][00276] Avg episode reward: [(0, '19.590')] [2023-02-24 07:25:30,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2768896. Throughput: 0: 847.6. Samples: 692708. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:25:30,342][00276] Avg episode reward: [(0, '19.331')] [2023-02-24 07:25:34,754][11622] Updated weights for policy 0, policy_version 680 (0.0035) [2023-02-24 07:25:35,339][00276] Fps is (10 sec: 2867.0, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2785280. Throughput: 0: 846.6. Samples: 694756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:25:35,342][00276] Avg episode reward: [(0, '21.901')] [2023-02-24 07:25:40,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2805760. Throughput: 0: 872.9. Samples: 701090. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:25:40,340][00276] Avg episode reward: [(0, '21.817')] [2023-02-24 07:25:45,269][11622] Updated weights for policy 0, policy_version 690 (0.0032) [2023-02-24 07:25:45,338][00276] Fps is (10 sec: 4096.3, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 2826240. Throughput: 0: 860.1. Samples: 706798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:25:45,345][00276] Avg episode reward: [(0, '21.618')] [2023-02-24 07:25:50,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2838528. Throughput: 0: 848.5. Samples: 708814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:25:50,343][00276] Avg episode reward: [(0, '21.882')] [2023-02-24 07:25:55,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2854912. Throughput: 0: 851.8. Samples: 713102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:25:55,341][00276] Avg episode reward: [(0, '21.713')] [2023-02-24 07:25:57,553][11622] Updated weights for policy 0, policy_version 700 (0.0016) [2023-02-24 07:26:00,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2875392. Throughput: 0: 880.7. Samples: 719388. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:26:00,345][00276] Avg episode reward: [(0, '22.487')] [2023-02-24 07:26:00,360][11606] Saving new best policy, reward=22.487! [2023-02-24 07:26:05,345][00276] Fps is (10 sec: 4093.3, 60 sec: 3481.2, 300 sec: 3373.9). Total num frames: 2895872. Throughput: 0: 880.9. Samples: 722534. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:26:05,353][00276] Avg episode reward: [(0, '21.488')] [2023-02-24 07:26:09,746][11622] Updated weights for policy 0, policy_version 710 (0.0031) [2023-02-24 07:26:10,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2908160. Throughput: 0: 844.4. Samples: 726702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:26:10,341][00276] Avg episode reward: [(0, '21.404')] [2023-02-24 07:26:15,338][00276] Fps is (10 sec: 2869.1, 60 sec: 3481.6, 300 sec: 3374.1). Total num frames: 2924544. Throughput: 0: 847.1. Samples: 730826. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:26:15,345][00276] Avg episode reward: [(0, '23.171')] [2023-02-24 07:26:15,351][11606] Saving new best policy, reward=23.171! [2023-02-24 07:26:20,339][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 2945024. Throughput: 0: 871.6. Samples: 733978. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:26:20,346][00276] Avg episode reward: [(0, '22.501')] [2023-02-24 07:26:21,235][11622] Updated weights for policy 0, policy_version 720 (0.0018) [2023-02-24 07:26:25,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 2961408. Throughput: 0: 870.4. Samples: 740258. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:26:25,343][00276] Avg episode reward: [(0, '23.390')] [2023-02-24 07:26:25,348][11606] Saving new best policy, reward=23.390! [2023-02-24 07:26:30,339][00276] Fps is (10 sec: 2867.0, 60 sec: 3413.3, 300 sec: 3346.3). Total num frames: 2973696. Throughput: 0: 831.9. Samples: 744232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:26:30,344][00276] Avg episode reward: [(0, '21.854')] [2023-02-24 07:26:35,041][11622] Updated weights for policy 0, policy_version 730 (0.0020) [2023-02-24 07:26:35,339][00276] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3360.2). Total num frames: 2990080. Throughput: 0: 831.5. Samples: 746232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:26:35,344][00276] Avg episode reward: [(0, '22.307')] [2023-02-24 07:26:40,338][00276] Fps is (10 sec: 3686.6, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 3010560. Throughput: 0: 858.2. Samples: 751720. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:26:40,344][00276] Avg episode reward: [(0, '23.036')] [2023-02-24 07:26:45,016][11622] Updated weights for policy 0, policy_version 740 (0.0015) [2023-02-24 07:26:45,349][00276] Fps is (10 sec: 4091.8, 60 sec: 3412.7, 300 sec: 3373.9). Total num frames: 3031040. Throughput: 0: 856.5. Samples: 757938. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:26:45,356][00276] Avg episode reward: [(0, '23.096')] [2023-02-24 07:26:50,339][00276] Fps is (10 sec: 3276.6, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 3043328. Throughput: 0: 833.1. Samples: 760018. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:26:50,346][00276] Avg episode reward: [(0, '23.149')] [2023-02-24 07:26:55,339][00276] Fps is (10 sec: 2460.1, 60 sec: 3345.0, 300 sec: 3346.2). Total num frames: 3055616. Throughput: 0: 829.6. Samples: 764036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:26:55,346][00276] Avg episode reward: [(0, '23.615')] [2023-02-24 07:26:55,349][11606] Saving new best policy, reward=23.615! [2023-02-24 07:26:58,566][11622] Updated weights for policy 0, policy_version 750 (0.0020) [2023-02-24 07:27:00,338][00276] Fps is (10 sec: 3277.0, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 3076096. Throughput: 0: 863.4. Samples: 769680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:27:00,341][00276] Avg episode reward: [(0, '24.013')] [2023-02-24 07:27:00,353][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000751_3076096.pth... [2023-02-24 07:27:00,519][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000556_2277376.pth [2023-02-24 07:27:00,549][11606] Saving new best policy, reward=24.013! [2023-02-24 07:27:05,338][00276] Fps is (10 sec: 4505.9, 60 sec: 3413.7, 300 sec: 3387.9). Total num frames: 3100672. Throughput: 0: 861.7. Samples: 772754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:27:05,345][00276] Avg episode reward: [(0, '22.116')] [2023-02-24 07:27:09,884][11622] Updated weights for policy 0, policy_version 760 (0.0027) [2023-02-24 07:27:10,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 3112960. Throughput: 0: 838.5. Samples: 777990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:27:10,345][00276] Avg episode reward: [(0, '21.760')] [2023-02-24 07:27:15,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 3125248. Throughput: 0: 840.3. Samples: 782046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:27:15,350][00276] Avg episode reward: [(0, '22.193')] [2023-02-24 07:27:20,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3141632. Throughput: 0: 847.9. Samples: 784386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:27:20,342][00276] Avg episode reward: [(0, '21.097')] [2023-02-24 07:27:24,402][11622] Updated weights for policy 0, policy_version 770 (0.0039) [2023-02-24 07:27:25,339][00276] Fps is (10 sec: 2867.0, 60 sec: 3208.5, 300 sec: 3332.3). Total num frames: 3153920. Throughput: 0: 817.3. Samples: 788500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:27:25,344][00276] Avg episode reward: [(0, '22.503')] [2023-02-24 07:27:30,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3208.6, 300 sec: 3304.6). Total num frames: 3166208. Throughput: 0: 761.6. Samples: 792204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:27:30,342][00276] Avg episode reward: [(0, '23.617')] [2023-02-24 07:27:35,341][00276] Fps is (10 sec: 2457.2, 60 sec: 3140.2, 300 sec: 3290.7). Total num frames: 3178496. Throughput: 0: 757.8. Samples: 794122. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:27:35,347][00276] Avg episode reward: [(0, '23.478')] [2023-02-24 07:27:39,213][11622] Updated weights for policy 0, policy_version 780 (0.0029) [2023-02-24 07:27:40,339][00276] Fps is (10 sec: 3276.7, 60 sec: 3140.2, 300 sec: 3318.4). Total num frames: 3198976. Throughput: 0: 767.4. Samples: 798570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:27:40,342][00276] Avg episode reward: [(0, '23.785')] [2023-02-24 07:27:45,338][00276] Fps is (10 sec: 4096.9, 60 sec: 3140.8, 300 sec: 3318.5). Total num frames: 3219456. Throughput: 0: 779.8. Samples: 804770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:27:45,341][00276] Avg episode reward: [(0, '24.697')] [2023-02-24 07:27:45,345][11606] Saving new best policy, reward=24.697! [2023-02-24 07:27:50,037][11622] Updated weights for policy 0, policy_version 790 (0.0018) [2023-02-24 07:27:50,338][00276] Fps is (10 sec: 3686.5, 60 sec: 3208.6, 300 sec: 3304.6). Total num frames: 3235840. Throughput: 0: 777.2. Samples: 807728. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:27:50,341][00276] Avg episode reward: [(0, '24.291')] [2023-02-24 07:27:55,339][00276] Fps is (10 sec: 2867.2, 60 sec: 3208.6, 300 sec: 3290.7). Total num frames: 3248128. Throughput: 0: 751.7. Samples: 811816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:27:55,345][00276] Avg episode reward: [(0, '24.310')] [2023-02-24 07:28:00,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 3264512. Throughput: 0: 769.2. Samples: 816662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:28:00,341][00276] Avg episode reward: [(0, '24.116')] [2023-02-24 07:28:02,730][11622] Updated weights for policy 0, policy_version 800 (0.0013) [2023-02-24 07:28:05,339][00276] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 3318.5). Total num frames: 3284992. Throughput: 0: 786.8. Samples: 819794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:28:05,345][00276] Avg episode reward: [(0, '24.287')] [2023-02-24 07:28:10,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 3305472. Throughput: 0: 830.6. Samples: 825878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:28:10,345][00276] Avg episode reward: [(0, '25.351')] [2023-02-24 07:28:10,359][11606] Saving new best policy, reward=25.351! [2023-02-24 07:28:14,649][11622] Updated weights for policy 0, policy_version 810 (0.0013) [2023-02-24 07:28:15,338][00276] Fps is (10 sec: 3276.9, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 3317760. Throughput: 0: 836.3. Samples: 829836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:28:15,342][00276] Avg episode reward: [(0, '24.909')] [2023-02-24 07:28:20,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 3334144. Throughput: 0: 838.9. Samples: 831870. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-24 07:28:20,341][00276] Avg episode reward: [(0, '23.933')] [2023-02-24 07:28:25,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3354624. Throughput: 0: 874.3. Samples: 837912. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-24 07:28:25,341][00276] Avg episode reward: [(0, '24.065')] [2023-02-24 07:28:25,601][11622] Updated weights for policy 0, policy_version 820 (0.0013) [2023-02-24 07:28:30,339][00276] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3332.3). Total num frames: 3375104. Throughput: 0: 874.9. Samples: 844142. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:28:30,343][00276] Avg episode reward: [(0, '22.476')] [2023-02-24 07:28:35,343][00276] Fps is (10 sec: 3275.4, 60 sec: 3481.5, 300 sec: 3318.4). Total num frames: 3387392. Throughput: 0: 853.3. Samples: 846132. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-24 07:28:35,346][00276] Avg episode reward: [(0, '20.866')] [2023-02-24 07:28:39,264][11622] Updated weights for policy 0, policy_version 830 (0.0019) [2023-02-24 07:28:40,339][00276] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 3399680. Throughput: 0: 851.2. Samples: 850122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:28:40,341][00276] Avg episode reward: [(0, '20.735')] [2023-02-24 07:28:45,338][00276] Fps is (10 sec: 3688.0, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 3424256. Throughput: 0: 881.4. Samples: 856324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:28:45,340][00276] Avg episode reward: [(0, '21.994')] [2023-02-24 07:28:48,603][11622] Updated weights for policy 0, policy_version 840 (0.0017) [2023-02-24 07:28:50,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3444736. Throughput: 0: 882.5. Samples: 859508. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:28:50,341][00276] Avg episode reward: [(0, '22.388')] [2023-02-24 07:28:55,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3457024. Throughput: 0: 852.9. Samples: 864258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-24 07:28:55,344][00276] Avg episode reward: [(0, '22.606')] [2023-02-24 07:29:00,338][00276] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 3469312. Throughput: 0: 857.2. Samples: 868412. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:29:00,341][00276] Avg episode reward: [(0, '23.091')] [2023-02-24 07:29:00,361][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000848_3473408.pth... [2023-02-24 07:29:00,477][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000652_2670592.pth [2023-02-24 07:29:02,284][11622] Updated weights for policy 0, policy_version 850 (0.0046) [2023-02-24 07:29:05,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3493888. Throughput: 0: 877.2. Samples: 871344. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:29:05,341][00276] Avg episode reward: [(0, '23.799')] [2023-02-24 07:29:10,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3514368. Throughput: 0: 884.5. Samples: 877716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:29:10,341][00276] Avg episode reward: [(0, '23.263')] [2023-02-24 07:29:12,899][11622] Updated weights for policy 0, policy_version 860 (0.0022) [2023-02-24 07:29:15,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 3526656. Throughput: 0: 847.8. Samples: 882292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:29:15,341][00276] Avg episode reward: [(0, '23.982')] [2023-02-24 07:29:20,339][00276] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 3538944. Throughput: 0: 847.6. Samples: 884272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:29:20,345][00276] Avg episode reward: [(0, '23.847')] [2023-02-24 07:29:25,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3559424. Throughput: 0: 872.6. Samples: 889390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:29:25,346][00276] Avg episode reward: [(0, '24.564')] [2023-02-24 07:29:25,691][11622] Updated weights for policy 0, policy_version 870 (0.0015) [2023-02-24 07:29:30,338][00276] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3579904. Throughput: 0: 875.1. Samples: 895704. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:29:30,341][00276] Avg episode reward: [(0, '24.223')] [2023-02-24 07:29:35,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3374.0). Total num frames: 3596288. Throughput: 0: 860.5. Samples: 898232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-24 07:29:35,346][00276] Avg episode reward: [(0, '24.560')] [2023-02-24 07:29:37,524][11622] Updated weights for policy 0, policy_version 880 (0.0013) [2023-02-24 07:29:40,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3608576. Throughput: 0: 847.8. Samples: 902408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:29:40,342][00276] Avg episode reward: [(0, '25.305')] [2023-02-24 07:29:45,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3629056. Throughput: 0: 871.6. Samples: 907632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:29:45,346][00276] Avg episode reward: [(0, '25.571')] [2023-02-24 07:29:45,350][11606] Saving new best policy, reward=25.571! [2023-02-24 07:29:48,806][11622] Updated weights for policy 0, policy_version 890 (0.0020) [2023-02-24 07:29:50,338][00276] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3649536. Throughput: 0: 874.7. Samples: 910706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:29:50,346][00276] Avg episode reward: [(0, '24.849')] [2023-02-24 07:29:55,341][00276] Fps is (10 sec: 3685.5, 60 sec: 3481.5, 300 sec: 3374.0). Total num frames: 3665920. Throughput: 0: 855.0. Samples: 916192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:29:55,347][00276] Avg episode reward: [(0, '24.051')] [2023-02-24 07:30:00,339][00276] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3678208. Throughput: 0: 842.2. Samples: 920190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:30:00,343][00276] Avg episode reward: [(0, '24.812')] [2023-02-24 07:30:02,416][11622] Updated weights for policy 0, policy_version 900 (0.0023) [2023-02-24 07:30:05,338][00276] Fps is (10 sec: 3277.6, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3698688. Throughput: 0: 846.0. Samples: 922340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:30:05,347][00276] Avg episode reward: [(0, '23.505')] [2023-02-24 07:30:10,339][00276] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3719168. Throughput: 0: 876.4. Samples: 928830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:30:10,346][00276] Avg episode reward: [(0, '23.976')] [2023-02-24 07:30:11,988][11622] Updated weights for policy 0, policy_version 910 (0.0014) [2023-02-24 07:30:15,340][00276] Fps is (10 sec: 3685.7, 60 sec: 3481.5, 300 sec: 3374.0). Total num frames: 3735552. Throughput: 0: 859.4. Samples: 934380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:30:15,348][00276] Avg episode reward: [(0, '24.970')] [2023-02-24 07:30:20,339][00276] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3747840. Throughput: 0: 849.7. Samples: 936468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:30:20,346][00276] Avg episode reward: [(0, '25.148')] [2023-02-24 07:30:25,193][11622] Updated weights for policy 0, policy_version 920 (0.0021) [2023-02-24 07:30:25,338][00276] Fps is (10 sec: 3277.4, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3768320. Throughput: 0: 854.2. Samples: 940846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:30:25,341][00276] Avg episode reward: [(0, '23.779')] [2023-02-24 07:30:30,339][00276] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3788800. Throughput: 0: 890.8. Samples: 947720. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:30:30,345][00276] Avg episode reward: [(0, '23.638')] [2023-02-24 07:30:35,087][11622] Updated weights for policy 0, policy_version 930 (0.0023) [2023-02-24 07:30:35,339][00276] Fps is (10 sec: 4095.7, 60 sec: 3549.8, 300 sec: 3401.8). Total num frames: 3809280. Throughput: 0: 896.7. Samples: 951056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-24 07:30:35,346][00276] Avg episode reward: [(0, '24.289')] [2023-02-24 07:30:40,342][00276] Fps is (10 sec: 3275.7, 60 sec: 3549.7, 300 sec: 3374.0). Total num frames: 3821568. Throughput: 0: 868.6. Samples: 955282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:30:40,344][00276] Avg episode reward: [(0, '23.999')] [2023-02-24 07:30:45,338][00276] Fps is (10 sec: 2457.8, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 3833856. Throughput: 0: 864.9. Samples: 959112. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-24 07:30:45,346][00276] Avg episode reward: [(0, '22.858')] [2023-02-24 07:30:50,336][11622] Updated weights for policy 0, policy_version 940 (0.0032) [2023-02-24 07:30:50,340][00276] Fps is (10 sec: 2867.8, 60 sec: 3345.0, 300 sec: 3374.0). Total num frames: 3850240. Throughput: 0: 864.2. Samples: 961232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-24 07:30:50,344][00276] Avg episode reward: [(0, '22.799')] [2023-02-24 07:30:55,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3276.9, 300 sec: 3346.2). Total num frames: 3862528. Throughput: 0: 814.5. Samples: 965482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:30:55,347][00276] Avg episode reward: [(0, '23.297')] [2023-02-24 07:31:00,338][00276] Fps is (10 sec: 2867.6, 60 sec: 3345.1, 300 sec: 3332.4). Total num frames: 3878912. Throughput: 0: 785.8. Samples: 969740. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:31:00,343][00276] Avg episode reward: [(0, '24.105')] [2023-02-24 07:31:00,356][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000947_3878912.pth... [2023-02-24 07:31:00,511][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000751_3076096.pth [2023-02-24 07:31:04,766][11622] Updated weights for policy 0, policy_version 950 (0.0036) [2023-02-24 07:31:05,338][00276] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3332.3). Total num frames: 3891200. Throughput: 0: 784.2. Samples: 971758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:31:05,341][00276] Avg episode reward: [(0, '25.193')] [2023-02-24 07:31:10,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3915776. Throughput: 0: 818.7. Samples: 977688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:31:10,342][00276] Avg episode reward: [(0, '25.205')] [2023-02-24 07:31:14,032][11622] Updated weights for policy 0, policy_version 960 (0.0015) [2023-02-24 07:31:15,338][00276] Fps is (10 sec: 4505.6, 60 sec: 3345.2, 300 sec: 3360.1). Total num frames: 3936256. Throughput: 0: 812.5. Samples: 984282. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:31:15,345][00276] Avg episode reward: [(0, '26.011')] [2023-02-24 07:31:15,353][11606] Saving new best policy, reward=26.011! [2023-02-24 07:31:20,338][00276] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 3948544. Throughput: 0: 783.1. Samples: 986294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:31:20,341][00276] Avg episode reward: [(0, '26.007')] [2023-02-24 07:31:25,343][00276] Fps is (10 sec: 2865.9, 60 sec: 3276.6, 300 sec: 3360.1). Total num frames: 3964928. Throughput: 0: 783.0. Samples: 990520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-24 07:31:25,350][00276] Avg episode reward: [(0, '25.693')] [2023-02-24 07:31:27,233][11622] Updated weights for policy 0, policy_version 970 (0.0023) [2023-02-24 07:31:30,338][00276] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 3985408. Throughput: 0: 831.6. Samples: 996532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-24 07:31:30,341][00276] Avg episode reward: [(0, '24.909')] [2023-02-24 07:31:34,661][11606] Stopping Batcher_0... [2023-02-24 07:31:34,662][11606] Loop batcher_evt_loop terminating... [2023-02-24 07:31:34,664][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-24 07:31:34,661][00276] Component Batcher_0 stopped! [2023-02-24 07:31:34,736][00276] Component RolloutWorker_w4 stopped! [2023-02-24 07:31:34,741][11628] Stopping RolloutWorker_w4... [2023-02-24 07:31:34,744][11628] Loop rollout_proc4_evt_loop terminating... [2023-02-24 07:31:34,754][11627] Stopping RolloutWorker_w3... [2023-02-24 07:31:34,755][00276] Component RolloutWorker_w3 stopped! [2023-02-24 07:31:34,767][11625] Stopping RolloutWorker_w1... [2023-02-24 07:31:34,763][00276] Component RolloutWorker_w6 stopped! [2023-02-24 07:31:34,769][00276] Component RolloutWorker_w1 stopped! [2023-02-24 07:31:34,773][11630] Stopping RolloutWorker_w6... [2023-02-24 07:31:34,774][11630] Loop rollout_proc6_evt_loop terminating... [2023-02-24 07:31:34,756][11627] Loop rollout_proc3_evt_loop terminating... [2023-02-24 07:31:34,770][11622] Weights refcount: 2 0 [2023-02-24 07:31:34,778][00276] Component RolloutWorker_w0 stopped! [2023-02-24 07:31:34,781][00276] Component InferenceWorker_p0-w0 stopped! [2023-02-24 07:31:34,785][11623] Stopping RolloutWorker_w0... [2023-02-24 07:31:34,785][11623] Loop rollout_proc0_evt_loop terminating... [2023-02-24 07:31:34,787][00276] Component RolloutWorker_w2 stopped! [2023-02-24 07:31:34,768][11625] Loop rollout_proc1_evt_loop terminating... [2023-02-24 07:31:34,793][11626] Stopping RolloutWorker_w2... [2023-02-24 07:31:34,793][11626] Loop rollout_proc2_evt_loop terminating... [2023-02-24 07:31:34,781][11622] Stopping InferenceWorker_p0-w0... [2023-02-24 07:31:34,795][11622] Loop inference_proc0-0_evt_loop terminating... [2023-02-24 07:31:34,799][11631] Stopping RolloutWorker_w7... [2023-02-24 07:31:34,802][11629] Stopping RolloutWorker_w5... [2023-02-24 07:31:34,799][00276] Component RolloutWorker_w7 stopped! [2023-02-24 07:31:34,805][00276] Component RolloutWorker_w5 stopped! [2023-02-24 07:31:34,801][11631] Loop rollout_proc7_evt_loop terminating... [2023-02-24 07:31:34,810][11629] Loop rollout_proc5_evt_loop terminating... [2023-02-24 07:31:34,862][11606] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000848_3473408.pth [2023-02-24 07:31:34,871][11606] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-24 07:31:35,044][00276] Component LearnerWorker_p0 stopped! [2023-02-24 07:31:35,052][00276] Waiting for process learner_proc0 to stop... [2023-02-24 07:31:35,056][11606] Stopping LearnerWorker_p0... [2023-02-24 07:31:35,057][11606] Loop learner_proc0_evt_loop terminating... [2023-02-24 07:31:37,448][00276] Waiting for process inference_proc0-0 to join... [2023-02-24 07:31:37,995][00276] Waiting for process rollout_proc0 to join... [2023-02-24 07:31:38,769][00276] Waiting for process rollout_proc1 to join... [2023-02-24 07:31:38,776][00276] Waiting for process rollout_proc2 to join... [2023-02-24 07:31:38,785][00276] Waiting for process rollout_proc3 to join... [2023-02-24 07:31:38,788][00276] Waiting for process rollout_proc4 to join... [2023-02-24 07:31:38,789][00276] Waiting for process rollout_proc5 to join... [2023-02-24 07:31:38,793][00276] Waiting for process rollout_proc6 to join... [2023-02-24 07:31:38,794][00276] Waiting for process rollout_proc7 to join... [2023-02-24 07:31:38,797][00276] Batcher 0 profile tree view: batching: 26.5869, releasing_batches: 0.0260 [2023-02-24 07:31:38,799][00276] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 592.0971 update_model: 8.5867 weight_update: 0.0022 one_step: 0.0058 handle_policy_step: 559.4981 deserialize: 15.7107, stack: 3.2457, obs_to_device_normalize: 119.9739, forward: 276.7932, send_messages: 27.9310 prepare_outputs: 88.6972 to_cpu: 54.6780 [2023-02-24 07:31:38,801][00276] Learner 0 profile tree view: misc: 0.0062, prepare_batch: 16.2868 train: 77.0420 epoch_init: 0.0063, minibatch_init: 0.0101, losses_postprocess: 0.5898, kl_divergence: 0.6338, after_optimizer: 33.0290 calculate_losses: 27.4369 losses_init: 0.0036, forward_head: 1.8855, bptt_initial: 17.9326, tail: 1.2940, advantages_returns: 0.3396, losses: 3.3699 bptt: 2.2763 bptt_forward_core: 2.1889 update: 14.6040 clip: 1.4507 [2023-02-24 07:31:38,802][00276] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.3633, enqueue_policy_requests: 167.4823, env_step: 895.5136, overhead: 24.4946, complete_rollouts: 7.1992 save_policy_outputs: 22.8314 split_output_tensors: 11.5229 [2023-02-24 07:31:38,806][00276] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.4573, enqueue_policy_requests: 172.3772, env_step: 891.7417, overhead: 24.6449, complete_rollouts: 7.5251 save_policy_outputs: 22.2699 split_output_tensors: 10.5410 [2023-02-24 07:31:38,807][00276] Loop Runner_EvtLoop terminating... [2023-02-24 07:31:38,809][00276] Runner profile tree view: main_loop: 1233.0327 [2023-02-24 07:31:38,810][00276] Collected {0: 4005888}, FPS: 3248.8 [2023-02-24 07:31:39,000][00276] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-24 07:31:39,002][00276] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-24 07:31:39,004][00276] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-24 07:31:39,006][00276] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-24 07:31:39,009][00276] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-24 07:31:39,010][00276] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-24 07:31:39,011][00276] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-02-24 07:31:39,012][00276] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-24 07:31:39,014][00276] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-02-24 07:31:39,015][00276] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-02-24 07:31:39,016][00276] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-24 07:31:39,017][00276] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-24 07:31:39,022][00276] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-24 07:31:39,023][00276] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-24 07:31:39,024][00276] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-24 07:31:39,057][00276] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-24 07:31:39,061][00276] RunningMeanStd input shape: (3, 72, 128) [2023-02-24 07:31:39,064][00276] RunningMeanStd input shape: (1,) [2023-02-24 07:31:39,088][00276] ConvEncoder: input_channels=3 [2023-02-24 07:31:39,913][00276] Conv encoder output size: 512 [2023-02-24 07:31:39,919][00276] Policy head output size: 512 [2023-02-24 07:31:42,311][00276] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-24 07:31:43,543][00276] Num frames 100... [2023-02-24 07:31:43,654][00276] Num frames 200... [2023-02-24 07:31:43,771][00276] Num frames 300... [2023-02-24 07:31:43,885][00276] Num frames 400... [2023-02-24 07:31:44,000][00276] Num frames 500... [2023-02-24 07:31:44,121][00276] Num frames 600... [2023-02-24 07:31:44,235][00276] Num frames 700... [2023-02-24 07:31:44,351][00276] Num frames 800... [2023-02-24 07:31:44,463][00276] Num frames 900... [2023-02-24 07:31:44,576][00276] Num frames 1000... [2023-02-24 07:31:44,688][00276] Num frames 1100... [2023-02-24 07:31:44,799][00276] Num frames 1200... [2023-02-24 07:31:44,913][00276] Num frames 1300... [2023-02-24 07:31:45,037][00276] Num frames 1400... [2023-02-24 07:31:45,151][00276] Num frames 1500... [2023-02-24 07:31:45,271][00276] Num frames 1600... [2023-02-24 07:31:45,411][00276] Avg episode rewards: #0: 43.769, true rewards: #0: 16.770 [2023-02-24 07:31:45,413][00276] Avg episode reward: 43.769, avg true_objective: 16.770 [2023-02-24 07:31:45,443][00276] Num frames 1700... [2023-02-24 07:31:45,562][00276] Num frames 1800... [2023-02-24 07:31:45,679][00276] Num frames 1900... [2023-02-24 07:31:45,796][00276] Num frames 2000... [2023-02-24 07:31:45,924][00276] Num frames 2100... [2023-02-24 07:31:46,047][00276] Num frames 2200... [2023-02-24 07:31:46,162][00276] Num frames 2300... [2023-02-24 07:31:46,276][00276] Num frames 2400... [2023-02-24 07:31:46,393][00276] Num frames 2500... [2023-02-24 07:31:46,503][00276] Num frames 2600... [2023-02-24 07:31:46,612][00276] Num frames 2700... [2023-02-24 07:31:46,730][00276] Num frames 2800... [2023-02-24 07:31:46,846][00276] Num frames 2900... [2023-02-24 07:31:46,969][00276] Num frames 3000... [2023-02-24 07:31:47,089][00276] Num frames 3100... [2023-02-24 07:31:47,199][00276] Num frames 3200... [2023-02-24 07:31:47,310][00276] Num frames 3300... [2023-02-24 07:31:47,422][00276] Num frames 3400... [2023-02-24 07:31:47,540][00276] Num frames 3500... [2023-02-24 07:31:47,677][00276] Avg episode rewards: #0: 47.854, true rewards: #0: 17.855 [2023-02-24 07:31:47,679][00276] Avg episode reward: 47.854, avg true_objective: 17.855 [2023-02-24 07:31:47,715][00276] Num frames 3600... [2023-02-24 07:31:47,833][00276] Num frames 3700... [2023-02-24 07:31:47,949][00276] Num frames 3800... [2023-02-24 07:31:48,068][00276] Num frames 3900... [2023-02-24 07:31:48,195][00276] Num frames 4000... [2023-02-24 07:31:48,313][00276] Num frames 4100... [2023-02-24 07:31:48,425][00276] Num frames 4200... [2023-02-24 07:31:48,540][00276] Num frames 4300... [2023-02-24 07:31:48,654][00276] Num frames 4400... [2023-02-24 07:31:48,773][00276] Num frames 4500... [2023-02-24 07:31:48,898][00276] Num frames 4600... [2023-02-24 07:31:49,022][00276] Num frames 4700... [2023-02-24 07:31:49,150][00276] Num frames 4800... [2023-02-24 07:31:49,236][00276] Avg episode rewards: #0: 42.733, true rewards: #0: 16.067 [2023-02-24 07:31:49,238][00276] Avg episode reward: 42.733, avg true_objective: 16.067 [2023-02-24 07:31:49,336][00276] Num frames 4900... [2023-02-24 07:31:49,446][00276] Num frames 5000... [2023-02-24 07:31:49,556][00276] Num frames 5100... [2023-02-24 07:31:49,664][00276] Num frames 5200... [2023-02-24 07:31:49,774][00276] Num frames 5300... [2023-02-24 07:31:49,891][00276] Num frames 5400... [2023-02-24 07:31:50,005][00276] Num frames 5500... [2023-02-24 07:31:50,134][00276] Num frames 5600... [2023-02-24 07:31:50,214][00276] Avg episode rewards: #0: 36.050, true rewards: #0: 14.050 [2023-02-24 07:31:50,215][00276] Avg episode reward: 36.050, avg true_objective: 14.050 [2023-02-24 07:31:50,309][00276] Num frames 5700... [2023-02-24 07:31:50,448][00276] Num frames 5800... [2023-02-24 07:31:50,616][00276] Num frames 5900... [2023-02-24 07:31:50,772][00276] Num frames 6000... [2023-02-24 07:31:50,927][00276] Num frames 6100... [2023-02-24 07:31:51,087][00276] Num frames 6200... [2023-02-24 07:31:51,249][00276] Num frames 6300... [2023-02-24 07:31:51,418][00276] Num frames 6400... [2023-02-24 07:31:51,632][00276] Avg episode rewards: #0: 33.196, true rewards: #0: 12.996 [2023-02-24 07:31:51,637][00276] Avg episode reward: 33.196, avg true_objective: 12.996 [2023-02-24 07:31:51,645][00276] Num frames 6500... [2023-02-24 07:31:51,815][00276] Num frames 6600... [2023-02-24 07:31:51,995][00276] Num frames 6700... [2023-02-24 07:31:52,171][00276] Num frames 6800... [2023-02-24 07:31:52,332][00276] Num frames 6900... [2023-02-24 07:31:52,492][00276] Num frames 7000... [2023-02-24 07:31:52,647][00276] Num frames 7100... [2023-02-24 07:31:52,806][00276] Num frames 7200... [2023-02-24 07:31:52,964][00276] Num frames 7300... [2023-02-24 07:31:53,128][00276] Num frames 7400... [2023-02-24 07:31:53,302][00276] Num frames 7500... [2023-02-24 07:31:53,460][00276] Num frames 7600... [2023-02-24 07:31:53,643][00276] Num frames 7700... [2023-02-24 07:31:53,823][00276] Num frames 7800... [2023-02-24 07:31:53,956][00276] Num frames 7900... [2023-02-24 07:31:54,070][00276] Num frames 8000... [2023-02-24 07:31:54,184][00276] Num frames 8100... [2023-02-24 07:31:54,312][00276] Num frames 8200... [2023-02-24 07:31:54,423][00276] Num frames 8300... [2023-02-24 07:31:54,534][00276] Num frames 8400... [2023-02-24 07:31:54,655][00276] Avg episode rewards: #0: 36.093, true rewards: #0: 14.093 [2023-02-24 07:31:54,656][00276] Avg episode reward: 36.093, avg true_objective: 14.093 [2023-02-24 07:31:54,715][00276] Num frames 8500... [2023-02-24 07:31:54,849][00276] Num frames 8600... [2023-02-24 07:31:54,972][00276] Num frames 8700... [2023-02-24 07:31:55,080][00276] Num frames 8800... [2023-02-24 07:31:55,192][00276] Num frames 8900... [2023-02-24 07:31:55,315][00276] Num frames 9000... [2023-02-24 07:31:55,427][00276] Num frames 9100... [2023-02-24 07:31:55,535][00276] Num frames 9200... [2023-02-24 07:31:55,656][00276] Num frames 9300... [2023-02-24 07:31:55,789][00276] Avg episode rewards: #0: 34.237, true rewards: #0: 13.380 [2023-02-24 07:31:55,792][00276] Avg episode reward: 34.237, avg true_objective: 13.380 [2023-02-24 07:31:55,835][00276] Num frames 9400... [2023-02-24 07:31:55,955][00276] Num frames 9500... [2023-02-24 07:31:56,073][00276] Num frames 9600... [2023-02-24 07:31:56,199][00276] Num frames 9700... [2023-02-24 07:31:56,316][00276] Num frames 9800... [2023-02-24 07:31:56,437][00276] Num frames 9900... [2023-02-24 07:31:56,549][00276] Num frames 10000... [2023-02-24 07:31:56,662][00276] Num frames 10100... [2023-02-24 07:31:56,774][00276] Num frames 10200... [2023-02-24 07:31:56,882][00276] Num frames 10300... [2023-02-24 07:31:56,994][00276] Num frames 10400... [2023-02-24 07:31:57,114][00276] Avg episode rewards: #0: 32.567, true rewards: #0: 13.067 [2023-02-24 07:31:57,117][00276] Avg episode reward: 32.567, avg true_objective: 13.067 [2023-02-24 07:31:57,170][00276] Num frames 10500... [2023-02-24 07:31:57,281][00276] Num frames 10600... [2023-02-24 07:31:57,402][00276] Num frames 10700... [2023-02-24 07:31:57,510][00276] Num frames 10800... [2023-02-24 07:31:57,625][00276] Num frames 10900... [2023-02-24 07:31:57,740][00276] Num frames 11000... [2023-02-24 07:31:57,866][00276] Avg episode rewards: #0: 29.958, true rewards: #0: 12.291 [2023-02-24 07:31:57,868][00276] Avg episode reward: 29.958, avg true_objective: 12.291 [2023-02-24 07:31:57,916][00276] Num frames 11100... [2023-02-24 07:31:58,032][00276] Num frames 11200... [2023-02-24 07:31:58,142][00276] Num frames 11300... [2023-02-24 07:31:58,255][00276] Num frames 11400... [2023-02-24 07:31:58,372][00276] Num frames 11500... [2023-02-24 07:31:58,481][00276] Avg episode rewards: #0: 27.842, true rewards: #0: 11.542 [2023-02-24 07:31:58,483][00276] Avg episode reward: 27.842, avg true_objective: 11.542 [2023-02-24 07:33:11,647][00276] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2023-02-24 07:56:46,830][00276] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-24 07:56:46,832][00276] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-24 07:56:46,834][00276] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-24 07:56:46,835][00276] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-24 07:56:46,838][00276] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-24 07:56:46,839][00276] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-24 07:56:46,840][00276] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-02-24 07:56:46,841][00276] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-24 07:56:46,842][00276] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-02-24 07:56:46,846][00276] Adding new argument 'hf_repository'='gaokaobishuati/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2023-02-24 07:56:46,847][00276] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-24 07:56:46,848][00276] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-24 07:56:46,852][00276] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-24 07:56:46,853][00276] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-24 07:56:46,857][00276] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-24 07:56:46,893][00276] RunningMeanStd input shape: (3, 72, 128) [2023-02-24 07:56:46,897][00276] RunningMeanStd input shape: (1,) [2023-02-24 07:56:46,914][00276] ConvEncoder: input_channels=3 [2023-02-24 07:56:46,974][00276] Conv encoder output size: 512 [2023-02-24 07:56:46,979][00276] Policy head output size: 512 [2023-02-24 07:56:47,008][00276] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-24 07:56:47,635][00276] Num frames 100... [2023-02-24 07:56:47,768][00276] Num frames 200... [2023-02-24 07:56:47,879][00276] Num frames 300... [2023-02-24 07:56:47,993][00276] Num frames 400... [2023-02-24 07:56:48,105][00276] Num frames 500... [2023-02-24 07:56:48,219][00276] Num frames 600... [2023-02-24 07:56:48,337][00276] Num frames 700... [2023-02-24 07:56:48,446][00276] Num frames 800... [2023-02-24 07:56:48,563][00276] Num frames 900... [2023-02-24 07:56:48,673][00276] Num frames 1000... [2023-02-24 07:56:48,789][00276] Num frames 1100... [2023-02-24 07:56:48,900][00276] Num frames 1200... [2023-02-24 07:56:49,022][00276] Num frames 1300... [2023-02-24 07:56:49,133][00276] Num frames 1400... [2023-02-24 07:56:49,244][00276] Num frames 1500... [2023-02-24 07:56:49,361][00276] Num frames 1600... [2023-02-24 07:56:49,472][00276] Num frames 1700... [2023-02-24 07:56:49,584][00276] Num frames 1800... [2023-02-24 07:56:49,696][00276] Num frames 1900... [2023-02-24 07:56:49,824][00276] Num frames 2000... [2023-02-24 07:56:49,942][00276] Num frames 2100... [2023-02-24 07:56:49,994][00276] Avg episode rewards: #0: 57.999, true rewards: #0: 21.000 [2023-02-24 07:56:49,996][00276] Avg episode reward: 57.999, avg true_objective: 21.000 [2023-02-24 07:56:50,119][00276] Num frames 2200... [2023-02-24 07:56:50,240][00276] Num frames 2300... [2023-02-24 07:56:50,352][00276] Num frames 2400... [2023-02-24 07:56:50,467][00276] Num frames 2500... [2023-02-24 07:56:50,576][00276] Num frames 2600... [2023-02-24 07:56:50,690][00276] Num frames 2700... [2023-02-24 07:56:50,805][00276] Num frames 2800... [2023-02-24 07:56:50,918][00276] Num frames 2900... [2023-02-24 07:56:51,025][00276] Num frames 3000... [2023-02-24 07:56:51,145][00276] Num frames 3100... [2023-02-24 07:56:51,257][00276] Num frames 3200... [2023-02-24 07:56:51,368][00276] Num frames 3300... [2023-02-24 07:56:51,479][00276] Num frames 3400... [2023-02-24 07:56:51,589][00276] Num frames 3500... [2023-02-24 07:56:51,707][00276] Num frames 3600... [2023-02-24 07:56:51,821][00276] Num frames 3700... [2023-02-24 07:56:51,933][00276] Num frames 3800... [2023-02-24 07:56:52,044][00276] Num frames 3900... [2023-02-24 07:56:52,159][00276] Num frames 4000... [2023-02-24 07:56:52,274][00276] Num frames 4100... [2023-02-24 07:56:52,395][00276] Num frames 4200... [2023-02-24 07:56:52,450][00276] Avg episode rewards: #0: 58.999, true rewards: #0: 21.000 [2023-02-24 07:56:52,453][00276] Avg episode reward: 58.999, avg true_objective: 21.000 [2023-02-24 07:56:52,580][00276] Num frames 4300... [2023-02-24 07:56:52,697][00276] Num frames 4400... [2023-02-24 07:56:52,818][00276] Num frames 4500... [2023-02-24 07:56:52,937][00276] Num frames 4600... [2023-02-24 07:56:53,053][00276] Num frames 4700... [2023-02-24 07:56:53,163][00276] Num frames 4800... [2023-02-24 07:56:53,298][00276] Avg episode rewards: #0: 43.849, true rewards: #0: 16.183 [2023-02-24 07:56:53,303][00276] Avg episode reward: 43.849, avg true_objective: 16.183 [2023-02-24 07:56:53,356][00276] Num frames 4900... [2023-02-24 07:56:53,462][00276] Num frames 5000... [2023-02-24 07:56:53,573][00276] Num frames 5100... [2023-02-24 07:56:53,692][00276] Num frames 5200... [2023-02-24 07:56:53,821][00276] Num frames 5300... [2023-02-24 07:56:53,933][00276] Num frames 5400... [2023-02-24 07:56:54,051][00276] Num frames 5500... [2023-02-24 07:56:54,143][00276] Avg episode rewards: #0: 35.824, true rewards: #0: 13.825 [2023-02-24 07:56:54,145][00276] Avg episode reward: 35.824, avg true_objective: 13.825 [2023-02-24 07:56:54,228][00276] Num frames 5600... [2023-02-24 07:56:54,344][00276] Num frames 5700... [2023-02-24 07:56:54,468][00276] Num frames 5800... [2023-02-24 07:56:54,579][00276] Num frames 5900... [2023-02-24 07:56:54,691][00276] Num frames 6000... [2023-02-24 07:56:54,807][00276] Num frames 6100... [2023-02-24 07:56:54,929][00276] Num frames 6200... [2023-02-24 07:56:55,052][00276] Num frames 6300... [2023-02-24 07:56:55,163][00276] Num frames 6400... [2023-02-24 07:56:55,265][00276] Avg episode rewards: #0: 32.684, true rewards: #0: 12.884 [2023-02-24 07:56:55,267][00276] Avg episode reward: 32.684, avg true_objective: 12.884 [2023-02-24 07:56:55,337][00276] Num frames 6500... [2023-02-24 07:56:55,451][00276] Num frames 6600... [2023-02-24 07:56:55,564][00276] Num frames 6700... [2023-02-24 07:56:55,677][00276] Num frames 6800... [2023-02-24 07:56:55,789][00276] Num frames 6900... [2023-02-24 07:56:55,912][00276] Avg episode rewards: #0: 29.091, true rewards: #0: 11.592 [2023-02-24 07:56:55,915][00276] Avg episode reward: 29.091, avg true_objective: 11.592 [2023-02-24 07:56:55,970][00276] Num frames 7000... [2023-02-24 07:56:56,079][00276] Num frames 7100... [2023-02-24 07:56:56,190][00276] Num frames 7200... [2023-02-24 07:56:56,307][00276] Num frames 7300... [2023-02-24 07:56:56,418][00276] Num frames 7400... [2023-02-24 07:56:56,534][00276] Num frames 7500... [2023-02-24 07:56:56,643][00276] Num frames 7600... [2023-02-24 07:56:56,753][00276] Num frames 7700... [2023-02-24 07:56:56,878][00276] Num frames 7800... [2023-02-24 07:56:56,988][00276] Num frames 7900... [2023-02-24 07:56:57,097][00276] Num frames 8000... [2023-02-24 07:56:57,209][00276] Num frames 8100... [2023-02-24 07:56:57,328][00276] Num frames 8200... [2023-02-24 07:56:57,440][00276] Num frames 8300... [2023-02-24 07:56:57,580][00276] Avg episode rewards: #0: 30.395, true rewards: #0: 11.967 [2023-02-24 07:56:57,582][00276] Avg episode reward: 30.395, avg true_objective: 11.967 [2023-02-24 07:56:57,609][00276] Num frames 8400... [2023-02-24 07:56:57,739][00276] Num frames 8500... [2023-02-24 07:56:57,904][00276] Num frames 8600... [2023-02-24 07:56:58,057][00276] Num frames 8700... [2023-02-24 07:56:58,216][00276] Num frames 8800... [2023-02-24 07:56:58,367][00276] Num frames 8900... [2023-02-24 07:56:58,516][00276] Num frames 9000... [2023-02-24 07:56:58,672][00276] Num frames 9100... [2023-02-24 07:56:58,837][00276] Num frames 9200... [2023-02-24 07:56:58,995][00276] Num frames 9300... [2023-02-24 07:56:59,151][00276] Num frames 9400... [2023-02-24 07:56:59,303][00276] Num frames 9500... [2023-02-24 07:56:59,459][00276] Num frames 9600... [2023-02-24 07:56:59,618][00276] Num frames 9700... [2023-02-24 07:56:59,681][00276] Avg episode rewards: #0: 30.501, true rewards: #0: 12.126 [2023-02-24 07:56:59,683][00276] Avg episode reward: 30.501, avg true_objective: 12.126 [2023-02-24 07:56:59,839][00276] Num frames 9800... [2023-02-24 07:57:00,000][00276] Num frames 9900... [2023-02-24 07:57:00,157][00276] Num frames 10000... [2023-02-24 07:57:00,316][00276] Num frames 10100... [2023-02-24 07:57:00,473][00276] Num frames 10200... [2023-02-24 07:57:00,636][00276] Num frames 10300... [2023-02-24 07:57:00,801][00276] Num frames 10400... [2023-02-24 07:57:00,976][00276] Num frames 10500... [2023-02-24 07:57:01,135][00276] Num frames 10600... [2023-02-24 07:57:01,258][00276] Num frames 10700... [2023-02-24 07:57:01,375][00276] Num frames 10800... [2023-02-24 07:57:01,469][00276] Avg episode rewards: #0: 29.815, true rewards: #0: 12.038 [2023-02-24 07:57:01,470][00276] Avg episode reward: 29.815, avg true_objective: 12.038 [2023-02-24 07:57:01,550][00276] Num frames 10900... [2023-02-24 07:57:01,661][00276] Num frames 11000... [2023-02-24 07:57:01,768][00276] Num frames 11100... [2023-02-24 07:57:01,882][00276] Num frames 11200... [2023-02-24 07:57:01,991][00276] Num frames 11300... [2023-02-24 07:57:02,107][00276] Num frames 11400... [2023-02-24 07:57:02,226][00276] Num frames 11500... [2023-02-24 07:57:02,338][00276] Num frames 11600... [2023-02-24 07:57:02,451][00276] Num frames 11700... [2023-02-24 07:57:02,563][00276] Num frames 11800... [2023-02-24 07:57:02,678][00276] Num frames 11900... [2023-02-24 07:57:02,795][00276] Num frames 12000... [2023-02-24 07:57:02,910][00276] Avg episode rewards: #0: 29.252, true rewards: #0: 12.052 [2023-02-24 07:57:02,913][00276] Avg episode reward: 29.252, avg true_objective: 12.052 [2023-02-24 07:58:20,789][00276] Replay video saved to /content/train_dir/default_experiment/replay.mp4!