| [2024-05-20 03:54:45,130][00361] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2024-05-20 03:54:45,133][00361] Rollout worker 0 uses device cpu | |
| [2024-05-20 03:54:45,134][00361] Rollout worker 1 uses device cpu | |
| [2024-05-20 03:54:45,135][00361] Rollout worker 2 uses device cpu | |
| [2024-05-20 03:54:45,137][00361] Rollout worker 3 uses device cpu | |
| [2024-05-20 03:54:45,138][00361] Rollout worker 4 uses device cpu | |
| [2024-05-20 03:54:45,139][00361] Rollout worker 5 uses device cpu | |
| [2024-05-20 03:54:45,140][00361] Rollout worker 6 uses device cpu | |
| [2024-05-20 03:54:45,142][00361] Rollout worker 7 uses device cpu | |
| [2024-05-20 03:54:45,307][00361] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-05-20 03:54:45,309][00361] InferenceWorker_p0-w0: min num requests: 2 | |
| [2024-05-20 03:54:45,344][00361] Starting all processes... | |
| [2024-05-20 03:54:45,345][00361] Starting process learner_proc0 | |
| [2024-05-20 03:54:46,139][00361] Starting all processes... | |
| [2024-05-20 03:54:46,150][00361] Starting process inference_proc0-0 | |
| [2024-05-20 03:54:46,150][00361] Starting process rollout_proc0 | |
| [2024-05-20 03:54:46,152][00361] Starting process rollout_proc1 | |
| [2024-05-20 03:54:46,152][00361] Starting process rollout_proc2 | |
| [2024-05-20 03:54:46,152][00361] Starting process rollout_proc3 | |
| [2024-05-20 03:54:46,152][00361] Starting process rollout_proc4 | |
| [2024-05-20 03:54:46,153][00361] Starting process rollout_proc5 | |
| [2024-05-20 03:54:46,153][00361] Starting process rollout_proc6 | |
| [2024-05-20 03:54:46,153][00361] Starting process rollout_proc7 | |
| [2024-05-20 03:55:00,768][03116] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-05-20 03:55:00,783][03116] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2024-05-20 03:55:00,829][03136] Worker 7 uses CPU cores [1] | |
| [2024-05-20 03:55:00,859][03116] Num visible devices: 1 | |
| [2024-05-20 03:55:00,898][03116] Starting seed is not provided | |
| [2024-05-20 03:55:00,899][03116] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-05-20 03:55:00,900][03116] Initializing actor-critic model on device cuda:0 | |
| [2024-05-20 03:55:00,901][03116] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-05-20 03:55:00,904][03116] RunningMeanStd input shape: (1,) | |
| [2024-05-20 03:55:00,917][03132] Worker 1 uses CPU cores [1] | |
| [2024-05-20 03:55:00,918][03129] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-05-20 03:55:00,924][03129] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2024-05-20 03:55:00,963][03133] Worker 3 uses CPU cores [1] | |
| [2024-05-20 03:55:00,970][03116] ConvEncoder: input_channels=3 | |
| [2024-05-20 03:55:00,992][03135] Worker 5 uses CPU cores [1] | |
| [2024-05-20 03:55:01,002][03129] Num visible devices: 1 | |
| [2024-05-20 03:55:01,020][03131] Worker 2 uses CPU cores [0] | |
| [2024-05-20 03:55:01,055][03134] Worker 4 uses CPU cores [0] | |
| [2024-05-20 03:55:01,085][03137] Worker 6 uses CPU cores [0] | |
| [2024-05-20 03:55:01,100][03130] Worker 0 uses CPU cores [0] | |
| [2024-05-20 03:55:01,237][03116] Conv encoder output size: 512 | |
| [2024-05-20 03:55:01,237][03116] Policy head output size: 512 | |
| [2024-05-20 03:55:01,289][03116] Created Actor Critic model with architecture: | |
| [2024-05-20 03:55:01,289][03116] 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) | |
| ) | |
| ) | |
| [2024-05-20 03:55:01,657][03116] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2024-05-20 03:55:03,355][03116] No checkpoints found | |
| [2024-05-20 03:55:03,355][03116] Did not load from checkpoint, starting from scratch! | |
| [2024-05-20 03:55:03,356][03116] Initialized policy 0 weights for model version 0 | |
| [2024-05-20 03:55:03,361][03116] LearnerWorker_p0 finished initialization! | |
| [2024-05-20 03:55:03,362][03116] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-05-20 03:55:03,430][00361] 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) | |
| [2024-05-20 03:55:03,598][03129] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-05-20 03:55:03,599][03129] RunningMeanStd input shape: (1,) | |
| [2024-05-20 03:55:03,612][03129] ConvEncoder: input_channels=3 | |
| [2024-05-20 03:55:03,718][03129] Conv encoder output size: 512 | |
| [2024-05-20 03:55:03,719][03129] Policy head output size: 512 | |
| [2024-05-20 03:55:03,771][00361] Inference worker 0-0 is ready! | |
| [2024-05-20 03:55:03,776][00361] All inference workers are ready! Signal rollout workers to start! | |
| [2024-05-20 03:55:04,023][03136] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,054][03130] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,063][03133] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,103][03137] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,104][03131] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,099][03134] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,108][03135] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:04,118][03132] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 03:55:05,218][03130] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:05,217][03134] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:05,299][00361] Heartbeat connected on Batcher_0 | |
| [2024-05-20 03:55:05,303][00361] Heartbeat connected on LearnerWorker_p0 | |
| [2024-05-20 03:55:05,341][00361] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2024-05-20 03:55:05,463][03136] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:05,476][03133] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:05,493][03135] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:06,036][03131] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:06,079][03130] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:06,464][03133] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:06,612][03132] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:07,669][03136] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:07,745][03134] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:08,280][03130] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:08,429][00361] 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) | |
| [2024-05-20 03:55:08,452][03135] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:08,616][03132] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:08,929][03133] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:09,405][03137] Decorrelating experience for 0 frames... | |
| [2024-05-20 03:55:09,896][03134] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:10,056][03130] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:10,343][00361] Heartbeat connected on RolloutWorker_w0 | |
| [2024-05-20 03:55:11,106][03132] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:11,411][03131] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:11,413][03137] Decorrelating experience for 32 frames... | |
| [2024-05-20 03:55:12,045][03134] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:12,351][00361] Heartbeat connected on RolloutWorker_w4 | |
| [2024-05-20 03:55:12,553][03133] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:12,819][00361] Heartbeat connected on RolloutWorker_w3 | |
| [2024-05-20 03:55:13,429][00361] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 26.8. Samples: 268. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-05-20 03:55:13,432][00361] Avg episode reward: [(0, '1.653')] | |
| [2024-05-20 03:55:13,441][03131] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:14,116][03132] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:14,407][00361] Heartbeat connected on RolloutWorker_w1 | |
| [2024-05-20 03:55:16,134][03131] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:16,866][00361] Heartbeat connected on RolloutWorker_w2 | |
| [2024-05-20 03:55:17,239][03116] Signal inference workers to stop experience collection... | |
| [2024-05-20 03:55:17,273][03129] InferenceWorker_p0-w0: stopping experience collection | |
| [2024-05-20 03:55:17,962][03137] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:18,429][00361] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 128.3. Samples: 1924. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-05-20 03:55:18,432][00361] Avg episode reward: [(0, '2.816')] | |
| [2024-05-20 03:55:18,509][03137] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:18,644][03135] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:18,940][00361] Heartbeat connected on RolloutWorker_w6 | |
| [2024-05-20 03:55:19,296][03116] Signal inference workers to resume experience collection... | |
| [2024-05-20 03:55:19,298][03129] InferenceWorker_p0-w0: resuming experience collection | |
| [2024-05-20 03:55:19,738][03136] Decorrelating experience for 64 frames... | |
| [2024-05-20 03:55:19,968][03135] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:20,523][00361] Heartbeat connected on RolloutWorker_w5 | |
| [2024-05-20 03:55:22,752][03136] Decorrelating experience for 96 frames... | |
| [2024-05-20 03:55:23,330][00361] Heartbeat connected on RolloutWorker_w7 | |
| [2024-05-20 03:55:23,429][00361] Fps is (10 sec: 1638.4, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 217.0. Samples: 4340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:55:23,433][00361] Avg episode reward: [(0, '3.296')] | |
| [2024-05-20 03:55:28,429][00361] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 329.5. Samples: 8238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:55:28,435][00361] Avg episode reward: [(0, '3.688')] | |
| [2024-05-20 03:55:30,992][03129] Updated weights for policy 0, policy_version 10 (0.0025) | |
| [2024-05-20 03:55:33,429][00361] Fps is (10 sec: 3276.8, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 49152. Throughput: 0: 353.8. Samples: 10614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:55:33,435][00361] Avg episode reward: [(0, '4.414')] | |
| [2024-05-20 03:55:38,429][00361] Fps is (10 sec: 4096.0, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 487.9. Samples: 17078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:55:38,434][00361] Avg episode reward: [(0, '4.541')] | |
| [2024-05-20 03:55:40,941][03129] Updated weights for policy 0, policy_version 20 (0.0019) | |
| [2024-05-20 03:55:43,429][00361] Fps is (10 sec: 3686.3, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 86016. Throughput: 0: 555.7. Samples: 22228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:55:43,434][00361] Avg episode reward: [(0, '4.499')] | |
| [2024-05-20 03:55:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 2184.6, 300 sec: 2184.6). Total num frames: 98304. Throughput: 0: 537.1. Samples: 24170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 03:55:48,436][00361] Avg episode reward: [(0, '4.487')] | |
| [2024-05-20 03:55:53,252][03129] Updated weights for policy 0, policy_version 30 (0.0028) | |
| [2024-05-20 03:55:53,429][00361] Fps is (10 sec: 3686.6, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 662.7. Samples: 29820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 03:55:53,436][00361] Avg episode reward: [(0, '4.305')] | |
| [2024-05-20 03:55:53,439][03116] Saving new best policy, reward=4.305! | |
| [2024-05-20 03:55:58,429][00361] Fps is (10 sec: 4096.0, 60 sec: 2532.1, 300 sec: 2532.1). Total num frames: 139264. Throughput: 0: 786.3. Samples: 35652. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:55:58,435][00361] Avg episode reward: [(0, '4.358')] | |
| [2024-05-20 03:55:58,447][03116] Saving new best policy, reward=4.358! | |
| [2024-05-20 03:56:03,433][00361] Fps is (10 sec: 2866.0, 60 sec: 2525.7, 300 sec: 2525.7). Total num frames: 151552. Throughput: 0: 789.2. Samples: 37442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:56:03,437][00361] Avg episode reward: [(0, '4.493')] | |
| [2024-05-20 03:56:03,441][03116] Saving new best policy, reward=4.493! | |
| [2024-05-20 03:56:06,057][03129] Updated weights for policy 0, policy_version 40 (0.0028) | |
| [2024-05-20 03:56:08,429][00361] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2646.7). Total num frames: 172032. Throughput: 0: 841.5. Samples: 42206. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:56:08,436][00361] Avg episode reward: [(0, '4.497')] | |
| [2024-05-20 03:56:08,448][03116] Saving new best policy, reward=4.497! | |
| [2024-05-20 03:56:13,429][00361] Fps is (10 sec: 4097.7, 60 sec: 3208.5, 300 sec: 2750.2). Total num frames: 192512. Throughput: 0: 895.4. Samples: 48532. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:56:13,432][00361] Avg episode reward: [(0, '4.330')] | |
| [2024-05-20 03:56:16,264][03129] Updated weights for policy 0, policy_version 50 (0.0020) | |
| [2024-05-20 03:56:18,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 208896. Throughput: 0: 905.8. Samples: 51376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:56:18,434][00361] Avg episode reward: [(0, '4.429')] | |
| [2024-05-20 03:56:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 2764.8). Total num frames: 221184. Throughput: 0: 847.5. Samples: 55214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:56:23,436][00361] Avg episode reward: [(0, '4.405')] | |
| [2024-05-20 03:56:28,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 2843.1). Total num frames: 241664. Throughput: 0: 864.6. Samples: 61134. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:56:28,434][00361] Avg episode reward: [(0, '4.471')] | |
| [2024-05-20 03:56:28,745][03129] Updated weights for policy 0, policy_version 60 (0.0045) | |
| [2024-05-20 03:56:33,430][00361] Fps is (10 sec: 4095.6, 60 sec: 3549.8, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 887.0. Samples: 64088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:56:33,438][00361] Avg episode reward: [(0, '4.469')] | |
| [2024-05-20 03:56:38,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 2888.8). Total num frames: 274432. Throughput: 0: 861.4. Samples: 68582. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:56:38,436][00361] Avg episode reward: [(0, '4.456')] | |
| [2024-05-20 03:56:38,452][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth... | |
| [2024-05-20 03:56:41,978][03129] Updated weights for policy 0, policy_version 70 (0.0026) | |
| [2024-05-20 03:56:43,429][00361] Fps is (10 sec: 2867.4, 60 sec: 3413.3, 300 sec: 2908.2). Total num frames: 290816. Throughput: 0: 834.6. Samples: 73208. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:56:43,435][00361] Avg episode reward: [(0, '4.512')] | |
| [2024-05-20 03:56:43,438][03116] Saving new best policy, reward=4.512! | |
| [2024-05-20 03:56:48,429][00361] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 2964.7). Total num frames: 311296. Throughput: 0: 860.9. Samples: 76180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:56:48,432][00361] Avg episode reward: [(0, '4.587')] | |
| [2024-05-20 03:56:48,440][03116] Saving new best policy, reward=4.587! | |
| [2024-05-20 03:56:53,092][03129] Updated weights for policy 0, policy_version 80 (0.0036) | |
| [2024-05-20 03:56:53,429][00361] Fps is (10 sec: 3686.5, 60 sec: 3413.3, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 879.0. Samples: 81760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:56:53,435][00361] Avg episode reward: [(0, '4.489')] | |
| [2024-05-20 03:56:58,429][00361] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 2956.3). Total num frames: 339968. Throughput: 0: 823.8. Samples: 85602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:56:58,436][00361] Avg episode reward: [(0, '4.511')] | |
| [2024-05-20 03:57:03,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.8, 300 sec: 3003.7). Total num frames: 360448. Throughput: 0: 829.0. Samples: 88682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:57:03,435][00361] Avg episode reward: [(0, '4.443')] | |
| [2024-05-20 03:57:04,826][03129] Updated weights for policy 0, policy_version 90 (0.0019) | |
| [2024-05-20 03:57:08,434][00361] Fps is (10 sec: 4094.0, 60 sec: 3481.3, 300 sec: 3047.3). Total num frames: 380928. Throughput: 0: 882.4. Samples: 94926. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:57:08,440][00361] Avg episode reward: [(0, '4.376')] | |
| [2024-05-20 03:57:13,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3024.7). Total num frames: 393216. Throughput: 0: 845.9. Samples: 99198. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 03:57:13,434][00361] Avg episode reward: [(0, '4.518')] | |
| [2024-05-20 03:57:17,595][03129] Updated weights for policy 0, policy_version 100 (0.0024) | |
| [2024-05-20 03:57:18,429][00361] Fps is (10 sec: 2868.5, 60 sec: 3345.0, 300 sec: 3034.1). Total num frames: 409600. Throughput: 0: 822.7. Samples: 101110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 03:57:18,437][00361] Avg episode reward: [(0, '4.542')] | |
| [2024-05-20 03:57:23,431][00361] Fps is (10 sec: 3276.2, 60 sec: 3413.2, 300 sec: 3042.7). Total num frames: 425984. Throughput: 0: 832.2. Samples: 106034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:57:23,433][00361] Avg episode reward: [(0, '4.696')] | |
| [2024-05-20 03:57:23,439][03116] Saving new best policy, reward=4.696! | |
| [2024-05-20 03:57:28,431][00361] Fps is (10 sec: 2866.8, 60 sec: 3276.7, 300 sec: 3022.5). Total num frames: 438272. Throughput: 0: 816.9. Samples: 109972. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:57:28,435][00361] Avg episode reward: [(0, '4.545')] | |
| [2024-05-20 03:57:32,601][03129] Updated weights for policy 0, policy_version 110 (0.0024) | |
| [2024-05-20 03:57:33,429][00361] Fps is (10 sec: 2458.0, 60 sec: 3140.3, 300 sec: 3003.7). Total num frames: 450560. Throughput: 0: 792.9. Samples: 111860. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:57:33,434][00361] Avg episode reward: [(0, '4.694')] | |
| [2024-05-20 03:57:38,429][00361] Fps is (10 sec: 3277.4, 60 sec: 3276.8, 300 sec: 3039.0). Total num frames: 471040. Throughput: 0: 789.9. Samples: 117306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:57:38,431][00361] Avg episode reward: [(0, '4.540')] | |
| [2024-05-20 03:57:42,688][03129] Updated weights for policy 0, policy_version 120 (0.0022) | |
| [2024-05-20 03:57:43,434][00361] Fps is (10 sec: 4094.0, 60 sec: 3344.8, 300 sec: 3071.9). Total num frames: 491520. Throughput: 0: 843.3. Samples: 123554. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:57:43,436][00361] Avg episode reward: [(0, '4.551')] | |
| [2024-05-20 03:57:48,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3053.4). Total num frames: 503808. Throughput: 0: 821.0. Samples: 125626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:57:48,434][00361] Avg episode reward: [(0, '4.551')] | |
| [2024-05-20 03:57:53,429][00361] Fps is (10 sec: 2868.6, 60 sec: 3208.5, 300 sec: 3060.0). Total num frames: 520192. Throughput: 0: 771.9. Samples: 129660. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:57:53,437][00361] Avg episode reward: [(0, '4.522')] | |
| [2024-05-20 03:57:55,672][03129] Updated weights for policy 0, policy_version 130 (0.0038) | |
| [2024-05-20 03:57:58,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3089.6). Total num frames: 540672. Throughput: 0: 815.2. Samples: 135882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:57:58,432][00361] Avg episode reward: [(0, '4.535')] | |
| [2024-05-20 03:58:03,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3117.5). Total num frames: 561152. Throughput: 0: 841.6. Samples: 138982. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:58:03,433][00361] Avg episode reward: [(0, '4.463')] | |
| [2024-05-20 03:58:08,433][00361] Fps is (10 sec: 2866.1, 60 sec: 3140.3, 300 sec: 3077.5). Total num frames: 569344. Throughput: 0: 819.2. Samples: 142900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 03:58:08,436][00361] Avg episode reward: [(0, '4.387')] | |
| [2024-05-20 03:58:08,469][03129] Updated weights for policy 0, policy_version 140 (0.0017) | |
| [2024-05-20 03:58:13,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3125.9). Total num frames: 593920. Throughput: 0: 862.2. Samples: 148770. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:13,437][00361] Avg episode reward: [(0, '4.325')] | |
| [2024-05-20 03:58:17,921][03129] Updated weights for policy 0, policy_version 150 (0.0017) | |
| [2024-05-20 03:58:18,429][00361] Fps is (10 sec: 4507.3, 60 sec: 3413.3, 300 sec: 3150.8). Total num frames: 614400. Throughput: 0: 891.8. Samples: 151992. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:18,431][00361] Avg episode reward: [(0, '4.403')] | |
| [2024-05-20 03:58:23,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3153.9). Total num frames: 630784. Throughput: 0: 885.0. Samples: 157130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:58:23,431][00361] Avg episode reward: [(0, '4.394')] | |
| [2024-05-20 03:58:28,429][00361] Fps is (10 sec: 2867.1, 60 sec: 3413.4, 300 sec: 3136.9). Total num frames: 643072. Throughput: 0: 848.1. Samples: 161716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:58:28,436][00361] Avg episode reward: [(0, '4.640')] | |
| [2024-05-20 03:58:30,531][03129] Updated weights for policy 0, policy_version 160 (0.0029) | |
| [2024-05-20 03:58:33,429][00361] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3179.3). Total num frames: 667648. Throughput: 0: 872.4. Samples: 164886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:33,432][00361] Avg episode reward: [(0, '4.721')] | |
| [2024-05-20 03:58:33,440][03116] Saving new best policy, reward=4.721! | |
| [2024-05-20 03:58:38,429][00361] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3181.5). Total num frames: 684032. Throughput: 0: 919.9. Samples: 171056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:38,431][00361] Avg episode reward: [(0, '4.587')] | |
| [2024-05-20 03:58:38,455][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000167_684032.pth... | |
| [2024-05-20 03:58:42,687][03129] Updated weights for policy 0, policy_version 170 (0.0025) | |
| [2024-05-20 03:58:43,429][00361] Fps is (10 sec: 2867.3, 60 sec: 3413.6, 300 sec: 3165.1). Total num frames: 696320. Throughput: 0: 866.8. Samples: 174888. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:43,433][00361] Avg episode reward: [(0, '4.606')] | |
| [2024-05-20 03:58:48,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3185.8). Total num frames: 716800. Throughput: 0: 860.9. Samples: 177722. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:58:48,435][00361] Avg episode reward: [(0, '4.737')] | |
| [2024-05-20 03:58:48,447][03116] Saving new best policy, reward=4.737! | |
| [2024-05-20 03:58:52,912][03129] Updated weights for policy 0, policy_version 180 (0.0035) | |
| [2024-05-20 03:58:53,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3205.6). Total num frames: 737280. Throughput: 0: 909.6. Samples: 183830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:58:53,432][00361] Avg episode reward: [(0, '4.899')] | |
| [2024-05-20 03:58:53,439][03116] Saving new best policy, reward=4.899! | |
| [2024-05-20 03:58:58,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3189.7). Total num frames: 749568. Throughput: 0: 882.0. Samples: 188460. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:58:58,437][00361] Avg episode reward: [(0, '4.839')] | |
| [2024-05-20 03:59:03,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3191.5). Total num frames: 765952. Throughput: 0: 854.0. Samples: 190422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:59:03,431][00361] Avg episode reward: [(0, '4.763')] | |
| [2024-05-20 03:59:05,606][03129] Updated weights for policy 0, policy_version 190 (0.0033) | |
| [2024-05-20 03:59:08,429][00361] Fps is (10 sec: 3686.3, 60 sec: 3618.3, 300 sec: 3209.9). Total num frames: 786432. Throughput: 0: 872.8. Samples: 196408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:59:08,432][00361] Avg episode reward: [(0, '4.770')] | |
| [2024-05-20 03:59:13,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3227.7). Total num frames: 806912. Throughput: 0: 899.7. Samples: 202204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:59:13,434][00361] Avg episode reward: [(0, '4.754')] | |
| [2024-05-20 03:59:17,710][03129] Updated weights for policy 0, policy_version 200 (0.0031) | |
| [2024-05-20 03:59:18,429][00361] Fps is (10 sec: 3276.9, 60 sec: 3413.3, 300 sec: 3212.6). Total num frames: 819200. Throughput: 0: 872.2. Samples: 204136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:59:18,435][00361] Avg episode reward: [(0, '4.669')] | |
| [2024-05-20 03:59:23,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3229.5). Total num frames: 839680. Throughput: 0: 840.6. Samples: 208884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 03:59:23,435][00361] Avg episode reward: [(0, '4.660')] | |
| [2024-05-20 03:59:28,178][03129] Updated weights for policy 0, policy_version 210 (0.0030) | |
| [2024-05-20 03:59:28,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3245.9). Total num frames: 860160. Throughput: 0: 898.1. Samples: 215304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:59:28,431][00361] Avg episode reward: [(0, '4.869')] | |
| [2024-05-20 03:59:33,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3231.3). Total num frames: 872448. Throughput: 0: 892.2. Samples: 217872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:59:33,436][00361] Avg episode reward: [(0, '4.866')] | |
| [2024-05-20 03:59:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3232.1). Total num frames: 888832. Throughput: 0: 842.2. Samples: 221728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 03:59:38,434][00361] Avg episode reward: [(0, '5.054')] | |
| [2024-05-20 03:59:38,442][03116] Saving new best policy, reward=5.054! | |
| [2024-05-20 03:59:40,651][03129] Updated weights for policy 0, policy_version 220 (0.0023) | |
| [2024-05-20 03:59:43,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3247.5). Total num frames: 909312. Throughput: 0: 879.7. Samples: 228048. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 03:59:43,432][00361] Avg episode reward: [(0, '4.698')] | |
| [2024-05-20 03:59:48,429][00361] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3262.4). Total num frames: 929792. Throughput: 0: 904.8. Samples: 231136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 03:59:48,436][00361] Avg episode reward: [(0, '4.778')] | |
| [2024-05-20 03:59:52,970][03129] Updated weights for policy 0, policy_version 230 (0.0029) | |
| [2024-05-20 03:59:53,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3248.6). Total num frames: 942080. Throughput: 0: 866.9. Samples: 235418. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 03:59:53,435][00361] Avg episode reward: [(0, '4.909')] | |
| [2024-05-20 03:59:58,429][00361] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3262.9). Total num frames: 962560. Throughput: 0: 856.3. Samples: 240738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 03:59:58,431][00361] Avg episode reward: [(0, '4.815')] | |
| [2024-05-20 04:00:03,183][03129] Updated weights for policy 0, policy_version 240 (0.0014) | |
| [2024-05-20 04:00:03,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3332.3). Total num frames: 983040. Throughput: 0: 883.1. Samples: 243874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:00:03,434][00361] Avg episode reward: [(0, '4.771')] | |
| [2024-05-20 04:00:08,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 995328. Throughput: 0: 897.9. Samples: 249288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:00:08,432][00361] Avg episode reward: [(0, '4.791')] | |
| [2024-05-20 04:00:13,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 1011712. Throughput: 0: 844.8. Samples: 253320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:00:13,435][00361] Avg episode reward: [(0, '4.853')] | |
| [2024-05-20 04:00:15,880][03129] Updated weights for policy 0, policy_version 250 (0.0022) | |
| [2024-05-20 04:00:18,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1032192. Throughput: 0: 859.1. Samples: 256532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:00:18,437][00361] Avg episode reward: [(0, '5.034')] | |
| [2024-05-20 04:00:23,436][00361] Fps is (10 sec: 4093.2, 60 sec: 3549.5, 300 sec: 3471.1). Total num frames: 1052672. Throughput: 0: 909.7. Samples: 262672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:00:23,439][00361] Avg episode reward: [(0, '5.016')] | |
| [2024-05-20 04:00:27,886][03129] Updated weights for policy 0, policy_version 260 (0.0031) | |
| [2024-05-20 04:00:28,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 1064960. Throughput: 0: 859.2. Samples: 266710. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:00:28,433][00361] Avg episode reward: [(0, '5.024')] | |
| [2024-05-20 04:00:33,429][00361] Fps is (10 sec: 2459.3, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 1077248. Throughput: 0: 842.0. Samples: 269028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:00:33,434][00361] Avg episode reward: [(0, '5.025')] | |
| [2024-05-20 04:00:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 1093632. Throughput: 0: 837.6. Samples: 273112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:00:38,436][00361] Avg episode reward: [(0, '5.205')] | |
| [2024-05-20 04:00:38,447][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000267_1093632.pth... | |
| [2024-05-20 04:00:38,594][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth | |
| [2024-05-20 04:00:38,610][03116] Saving new best policy, reward=5.205! | |
| [2024-05-20 04:00:41,274][03129] Updated weights for policy 0, policy_version 270 (0.0026) | |
| [2024-05-20 04:00:43,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3429.5). Total num frames: 1110016. Throughput: 0: 829.1. Samples: 278046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:00:43,432][00361] Avg episode reward: [(0, '5.328')] | |
| [2024-05-20 04:00:43,438][03116] Saving new best policy, reward=5.328! | |
| [2024-05-20 04:00:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 1122304. Throughput: 0: 798.8. Samples: 279818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:00:48,432][00361] Avg episode reward: [(0, '5.507')] | |
| [2024-05-20 04:00:48,440][03116] Saving new best policy, reward=5.507! | |
| [2024-05-20 04:00:53,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 1142784. Throughput: 0: 796.2. Samples: 285118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:00:53,432][00361] Avg episode reward: [(0, '5.546')] | |
| [2024-05-20 04:00:53,434][03116] Saving new best policy, reward=5.546! | |
| [2024-05-20 04:00:53,998][03129] Updated weights for policy 0, policy_version 280 (0.0021) | |
| [2024-05-20 04:00:58,432][00361] Fps is (10 sec: 4094.9, 60 sec: 3344.9, 300 sec: 3429.5). Total num frames: 1163264. Throughput: 0: 837.1. Samples: 290994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:00:58,434][00361] Avg episode reward: [(0, '5.682')] | |
| [2024-05-20 04:00:58,454][03116] Saving new best policy, reward=5.682! | |
| [2024-05-20 04:01:03,430][00361] Fps is (10 sec: 2867.0, 60 sec: 3140.2, 300 sec: 3387.9). Total num frames: 1171456. Throughput: 0: 805.5. Samples: 292782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:01:03,434][00361] Avg episode reward: [(0, '5.529')] | |
| [2024-05-20 04:01:07,340][03129] Updated weights for policy 0, policy_version 290 (0.0026) | |
| [2024-05-20 04:01:08,429][00361] Fps is (10 sec: 2868.0, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1191936. Throughput: 0: 763.1. Samples: 297006. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:01:08,434][00361] Avg episode reward: [(0, '5.388')] | |
| [2024-05-20 04:01:13,429][00361] Fps is (10 sec: 3686.6, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1208320. Throughput: 0: 801.7. Samples: 302788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:01:13,435][00361] Avg episode reward: [(0, '5.304')] | |
| [2024-05-20 04:01:18,431][00361] Fps is (10 sec: 3276.2, 60 sec: 3208.4, 300 sec: 3401.7). Total num frames: 1224704. Throughput: 0: 813.1. Samples: 305618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:01:18,435][00361] Avg episode reward: [(0, '5.564')] | |
| [2024-05-20 04:01:19,546][03129] Updated weights for policy 0, policy_version 300 (0.0018) | |
| [2024-05-20 04:01:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3072.4, 300 sec: 3374.0). Total num frames: 1236992. Throughput: 0: 801.1. Samples: 309160. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:01:23,431][00361] Avg episode reward: [(0, '5.254')] | |
| [2024-05-20 04:01:28,429][00361] Fps is (10 sec: 3277.4, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 1257472. Throughput: 0: 813.4. Samples: 314650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:01:28,431][00361] Avg episode reward: [(0, '5.663')] | |
| [2024-05-20 04:01:31,243][03129] Updated weights for policy 0, policy_version 310 (0.0020) | |
| [2024-05-20 04:01:33,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 1277952. Throughput: 0: 840.7. Samples: 317648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:01:33,432][00361] Avg episode reward: [(0, '5.771')] | |
| [2024-05-20 04:01:33,437][03116] Saving new best policy, reward=5.771! | |
| [2024-05-20 04:01:38,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1290240. Throughput: 0: 819.5. Samples: 321994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:01:38,433][00361] Avg episode reward: [(0, '5.864')] | |
| [2024-05-20 04:01:38,447][03116] Saving new best policy, reward=5.864! | |
| [2024-05-20 04:01:43,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3360.1). Total num frames: 1302528. Throughput: 0: 787.5. Samples: 326430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:01:43,437][00361] Avg episode reward: [(0, '5.822')] | |
| [2024-05-20 04:01:44,702][03129] Updated weights for policy 0, policy_version 320 (0.0036) | |
| [2024-05-20 04:01:48,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 1323008. Throughput: 0: 813.5. Samples: 329390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:01:48,431][00361] Avg episode reward: [(0, '5.970')] | |
| [2024-05-20 04:01:48,442][03116] Saving new best policy, reward=5.970! | |
| [2024-05-20 04:01:53,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1339392. Throughput: 0: 841.8. Samples: 334886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:01:53,436][00361] Avg episode reward: [(0, '6.092')] | |
| [2024-05-20 04:01:53,448][03116] Saving new best policy, reward=6.092! | |
| [2024-05-20 04:01:57,950][03129] Updated weights for policy 0, policy_version 330 (0.0028) | |
| [2024-05-20 04:01:58,431][00361] Fps is (10 sec: 2866.7, 60 sec: 3140.3, 300 sec: 3360.1). Total num frames: 1351680. Throughput: 0: 794.6. Samples: 338548. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 04:01:58,435][00361] Avg episode reward: [(0, '6.313')] | |
| [2024-05-20 04:01:58,449][03116] Saving new best policy, reward=6.313! | |
| [2024-05-20 04:02:03,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3346.3). Total num frames: 1368064. Throughput: 0: 787.6. Samples: 341060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:02:03,434][00361] Avg episode reward: [(0, '6.830')] | |
| [2024-05-20 04:02:03,473][03116] Saving new best policy, reward=6.830! | |
| [2024-05-20 04:02:08,371][03129] Updated weights for policy 0, policy_version 340 (0.0031) | |
| [2024-05-20 04:02:08,429][00361] Fps is (10 sec: 4096.7, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 1392640. Throughput: 0: 841.2. Samples: 347014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:02:08,434][00361] Avg episode reward: [(0, '7.125')] | |
| [2024-05-20 04:02:08,443][03116] Saving new best policy, reward=7.125! | |
| [2024-05-20 04:02:13,434][00361] Fps is (10 sec: 3275.2, 60 sec: 3208.3, 300 sec: 3360.1). Total num frames: 1400832. Throughput: 0: 814.6. Samples: 351310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:02:13,436][00361] Avg episode reward: [(0, '6.893')] | |
| [2024-05-20 04:02:18,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.6, 300 sec: 3360.1). Total num frames: 1417216. Throughput: 0: 789.7. Samples: 353186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:02:18,434][00361] Avg episode reward: [(0, '6.663')] | |
| [2024-05-20 04:02:21,890][03129] Updated weights for policy 0, policy_version 350 (0.0014) | |
| [2024-05-20 04:02:23,429][00361] Fps is (10 sec: 3688.1, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 1437696. Throughput: 0: 823.4. Samples: 359046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:02:23,437][00361] Avg episode reward: [(0, '6.432')] | |
| [2024-05-20 04:02:28,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 1454080. Throughput: 0: 845.7. Samples: 364486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:02:28,435][00361] Avg episode reward: [(0, '6.486')] | |
| [2024-05-20 04:02:33,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 1470464. Throughput: 0: 822.0. Samples: 366378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:02:33,434][00361] Avg episode reward: [(0, '6.584')] | |
| [2024-05-20 04:02:34,857][03129] Updated weights for policy 0, policy_version 360 (0.0029) | |
| [2024-05-20 04:02:38,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 1486848. Throughput: 0: 805.6. Samples: 371140. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:02:38,436][00361] Avg episode reward: [(0, '6.922')] | |
| [2024-05-20 04:02:38,445][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000363_1486848.pth... | |
| [2024-05-20 04:02:38,560][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000167_684032.pth | |
| [2024-05-20 04:02:43,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1507328. Throughput: 0: 860.9. Samples: 377288. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:02:43,431][00361] Avg episode reward: [(0, '6.816')] | |
| [2024-05-20 04:02:45,141][03129] Updated weights for policy 0, policy_version 370 (0.0020) | |
| [2024-05-20 04:02:48,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 1519616. Throughput: 0: 857.9. Samples: 379664. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:02:48,437][00361] Avg episode reward: [(0, '6.891')] | |
| [2024-05-20 04:02:53,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 1536000. Throughput: 0: 806.8. Samples: 383318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:02:53,436][00361] Avg episode reward: [(0, '6.847')] | |
| [2024-05-20 04:02:58,215][03129] Updated weights for policy 0, policy_version 380 (0.0024) | |
| [2024-05-20 04:02:58,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3374.0). Total num frames: 1556480. Throughput: 0: 843.0. Samples: 389242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:02:58,431][00361] Avg episode reward: [(0, '6.878')] | |
| [2024-05-20 04:03:03,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1572864. Throughput: 0: 867.7. Samples: 392232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:03:03,436][00361] Avg episode reward: [(0, '6.997')] | |
| [2024-05-20 04:03:08,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3360.1). Total num frames: 1585152. Throughput: 0: 828.6. Samples: 396332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:03:08,432][00361] Avg episode reward: [(0, '7.024')] | |
| [2024-05-20 04:03:11,635][03129] Updated weights for policy 0, policy_version 390 (0.0021) | |
| [2024-05-20 04:03:13,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.3, 300 sec: 3346.2). Total num frames: 1601536. Throughput: 0: 812.0. Samples: 401024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:03:13,432][00361] Avg episode reward: [(0, '7.167')] | |
| [2024-05-20 04:03:13,438][03116] Saving new best policy, reward=7.167! | |
| [2024-05-20 04:03:18,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1622016. Throughput: 0: 833.5. Samples: 403886. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:03:18,437][00361] Avg episode reward: [(0, '7.141')] | |
| [2024-05-20 04:03:23,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 1634304. Throughput: 0: 836.2. Samples: 408768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:03:23,431][00361] Avg episode reward: [(0, '7.438')] | |
| [2024-05-20 04:03:23,433][03116] Saving new best policy, reward=7.438! | |
| [2024-05-20 04:03:24,448][03129] Updated weights for policy 0, policy_version 400 (0.0029) | |
| [2024-05-20 04:03:28,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 1646592. Throughput: 0: 778.7. Samples: 412328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:03:28,432][00361] Avg episode reward: [(0, '7.623')] | |
| [2024-05-20 04:03:28,444][03116] Saving new best policy, reward=7.623! | |
| [2024-05-20 04:03:33,429][00361] Fps is (10 sec: 3276.7, 60 sec: 3276.8, 300 sec: 3332.3). Total num frames: 1667072. Throughput: 0: 792.7. Samples: 415336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:03:33,432][00361] Avg episode reward: [(0, '7.974')] | |
| [2024-05-20 04:03:33,439][03116] Saving new best policy, reward=7.974! | |
| [2024-05-20 04:03:36,149][03129] Updated weights for policy 0, policy_version 410 (0.0031) | |
| [2024-05-20 04:03:38,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 1687552. Throughput: 0: 841.7. Samples: 421196. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:03:38,432][00361] Avg episode reward: [(0, '7.874')] | |
| [2024-05-20 04:03:43,431][00361] Fps is (10 sec: 2866.6, 60 sec: 3140.1, 300 sec: 3318.4). Total num frames: 1695744. Throughput: 0: 795.4. Samples: 425038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:03:43,437][00361] Avg episode reward: [(0, '7.589')] | |
| [2024-05-20 04:03:48,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 1712128. Throughput: 0: 773.5. Samples: 427038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:03:48,436][00361] Avg episode reward: [(0, '7.657')] | |
| [2024-05-20 04:03:49,750][03129] Updated weights for policy 0, policy_version 420 (0.0019) | |
| [2024-05-20 04:03:53,429][00361] Fps is (10 sec: 3277.6, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 1728512. Throughput: 0: 793.2. Samples: 432024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:03:53,433][00361] Avg episode reward: [(0, '7.785')] | |
| [2024-05-20 04:03:58,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3304.6). Total num frames: 1740800. Throughput: 0: 766.8. Samples: 435528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:03:58,433][00361] Avg episode reward: [(0, '8.006')] | |
| [2024-05-20 04:03:58,452][03116] Saving new best policy, reward=8.006! | |
| [2024-05-20 04:04:03,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3276.8). Total num frames: 1753088. Throughput: 0: 743.4. Samples: 437338. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 04:04:03,438][00361] Avg episode reward: [(0, '8.496')] | |
| [2024-05-20 04:04:03,442][03116] Saving new best policy, reward=8.496! | |
| [2024-05-20 04:04:05,428][03129] Updated weights for policy 0, policy_version 430 (0.0029) | |
| [2024-05-20 04:04:08,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3276.8). Total num frames: 1773568. Throughput: 0: 749.6. Samples: 442500. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:04:08,432][00361] Avg episode reward: [(0, '8.700')] | |
| [2024-05-20 04:04:08,449][03116] Saving new best policy, reward=8.700! | |
| [2024-05-20 04:04:13,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3290.7). Total num frames: 1789952. Throughput: 0: 804.5. Samples: 448530. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-05-20 04:04:13,435][00361] Avg episode reward: [(0, '9.360')] | |
| [2024-05-20 04:04:13,556][03116] Saving new best policy, reward=9.360! | |
| [2024-05-20 04:04:17,321][03129] Updated weights for policy 0, policy_version 440 (0.0032) | |
| [2024-05-20 04:04:18,429][00361] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3262.9). Total num frames: 1802240. Throughput: 0: 777.4. Samples: 450318. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:04:18,432][00361] Avg episode reward: [(0, '8.779')] | |
| [2024-05-20 04:04:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3249.0). Total num frames: 1818624. Throughput: 0: 737.0. Samples: 454362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:04:23,432][00361] Avg episode reward: [(0, '8.639')] | |
| [2024-05-20 04:04:28,429][00361] Fps is (10 sec: 3686.5, 60 sec: 3208.5, 300 sec: 3276.8). Total num frames: 1839104. Throughput: 0: 780.8. Samples: 460170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:04:28,434][00361] Avg episode reward: [(0, '8.588')] | |
| [2024-05-20 04:04:29,139][03129] Updated weights for policy 0, policy_version 450 (0.0014) | |
| [2024-05-20 04:04:33,432][00361] Fps is (10 sec: 3685.4, 60 sec: 3140.1, 300 sec: 3276.8). Total num frames: 1855488. Throughput: 0: 799.4. Samples: 463014. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:04:33,435][00361] Avg episode reward: [(0, '8.219')] | |
| [2024-05-20 04:04:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3249.0). Total num frames: 1867776. Throughput: 0: 769.6. Samples: 466658. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:04:38,432][00361] Avg episode reward: [(0, '8.738')] | |
| [2024-05-20 04:04:38,448][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000456_1867776.pth... | |
| [2024-05-20 04:04:38,583][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000267_1093632.pth | |
| [2024-05-20 04:04:42,313][03129] Updated weights for policy 0, policy_version 460 (0.0026) | |
| [2024-05-20 04:04:43,429][00361] Fps is (10 sec: 3277.7, 60 sec: 3208.7, 300 sec: 3249.0). Total num frames: 1888256. Throughput: 0: 810.6. Samples: 472006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:04:43,434][00361] Avg episode reward: [(0, '8.598')] | |
| [2024-05-20 04:04:48,433][00361] Fps is (10 sec: 3685.1, 60 sec: 3208.3, 300 sec: 3262.9). Total num frames: 1904640. Throughput: 0: 836.4. Samples: 474980. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2024-05-20 04:04:48,436][00361] Avg episode reward: [(0, '9.002')] | |
| [2024-05-20 04:04:53,430][00361] Fps is (10 sec: 2867.0, 60 sec: 3140.2, 300 sec: 3235.1). Total num frames: 1916928. Throughput: 0: 826.3. Samples: 479684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:04:53,433][00361] Avg episode reward: [(0, '8.923')] | |
| [2024-05-20 04:04:55,477][03129] Updated weights for policy 0, policy_version 470 (0.0034) | |
| [2024-05-20 04:04:58,429][00361] Fps is (10 sec: 2868.3, 60 sec: 3208.5, 300 sec: 3221.3). Total num frames: 1933312. Throughput: 0: 791.1. Samples: 484128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:04:58,437][00361] Avg episode reward: [(0, '9.281')] | |
| [2024-05-20 04:05:03,429][00361] Fps is (10 sec: 4096.3, 60 sec: 3413.3, 300 sec: 3262.9). Total num frames: 1957888. Throughput: 0: 821.0. Samples: 487264. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:05:03,437][00361] Avg episode reward: [(0, '9.717')] | |
| [2024-05-20 04:05:03,444][03116] Saving new best policy, reward=9.717! | |
| [2024-05-20 04:05:05,606][03129] Updated weights for policy 0, policy_version 480 (0.0036) | |
| [2024-05-20 04:05:08,430][00361] Fps is (10 sec: 4095.7, 60 sec: 3345.0, 300 sec: 3262.9). Total num frames: 1974272. Throughput: 0: 862.2. Samples: 493162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:05:08,437][00361] Avg episode reward: [(0, '9.655')] | |
| [2024-05-20 04:05:13,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3235.1). Total num frames: 1986560. Throughput: 0: 819.6. Samples: 497050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:05:13,432][00361] Avg episode reward: [(0, '9.422')] | |
| [2024-05-20 04:05:18,195][03129] Updated weights for policy 0, policy_version 490 (0.0023) | |
| [2024-05-20 04:05:18,429][00361] Fps is (10 sec: 3277.0, 60 sec: 3413.3, 300 sec: 3235.2). Total num frames: 2007040. Throughput: 0: 816.4. Samples: 499752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:05:18,437][00361] Avg episode reward: [(0, '9.455')] | |
| [2024-05-20 04:05:23,430][00361] Fps is (10 sec: 4095.7, 60 sec: 3481.6, 300 sec: 3262.9). Total num frames: 2027520. Throughput: 0: 873.9. Samples: 505984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:05:23,432][00361] Avg episode reward: [(0, '9.450')] | |
| [2024-05-20 04:05:28,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3262.9). Total num frames: 2039808. Throughput: 0: 855.0. Samples: 510480. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:05:28,435][00361] Avg episode reward: [(0, '9.585')] | |
| [2024-05-20 04:05:30,882][03129] Updated weights for policy 0, policy_version 500 (0.0051) | |
| [2024-05-20 04:05:33,429][00361] Fps is (10 sec: 2867.4, 60 sec: 3345.2, 300 sec: 3262.9). Total num frames: 2056192. Throughput: 0: 832.5. Samples: 512438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:05:33,437][00361] Avg episode reward: [(0, '10.745')] | |
| [2024-05-20 04:05:33,439][03116] Saving new best policy, reward=10.745! | |
| [2024-05-20 04:05:38,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 2076672. Throughput: 0: 859.9. Samples: 518380. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:05:38,436][00361] Avg episode reward: [(0, '10.695')] | |
| [2024-05-20 04:05:41,135][03129] Updated weights for policy 0, policy_version 510 (0.0023) | |
| [2024-05-20 04:05:43,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3290.7). Total num frames: 2093056. Throughput: 0: 887.5. Samples: 524066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:05:43,434][00361] Avg episode reward: [(0, '11.166')] | |
| [2024-05-20 04:05:43,438][03116] Saving new best policy, reward=11.166! | |
| [2024-05-20 04:05:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.3, 300 sec: 3262.9). Total num frames: 2105344. Throughput: 0: 858.4. Samples: 525892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:05:48,431][00361] Avg episode reward: [(0, '10.884')] | |
| [2024-05-20 04:05:53,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3262.9). Total num frames: 2125824. Throughput: 0: 838.4. Samples: 530888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:05:53,432][00361] Avg episode reward: [(0, '10.771')] | |
| [2024-05-20 04:05:53,995][03129] Updated weights for policy 0, policy_version 520 (0.0033) | |
| [2024-05-20 04:05:58,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3304.6). Total num frames: 2146304. Throughput: 0: 887.7. Samples: 536998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:05:58,437][00361] Avg episode reward: [(0, '11.286')] | |
| [2024-05-20 04:05:58,450][03116] Saving new best policy, reward=11.286! | |
| [2024-05-20 04:06:03,432][00361] Fps is (10 sec: 3276.0, 60 sec: 3344.9, 300 sec: 3276.8). Total num frames: 2158592. Throughput: 0: 881.5. Samples: 539422. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:06:03,434][00361] Avg episode reward: [(0, '11.785')] | |
| [2024-05-20 04:06:03,436][03116] Saving new best policy, reward=11.785! | |
| [2024-05-20 04:06:07,056][03129] Updated weights for policy 0, policy_version 530 (0.0026) | |
| [2024-05-20 04:06:08,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3276.8). Total num frames: 2174976. Throughput: 0: 825.3. Samples: 543124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:06:08,432][00361] Avg episode reward: [(0, '12.160')] | |
| [2024-05-20 04:06:08,442][03116] Saving new best policy, reward=12.160! | |
| [2024-05-20 04:06:13,429][00361] Fps is (10 sec: 3687.3, 60 sec: 3481.6, 300 sec: 3290.7). Total num frames: 2195456. Throughput: 0: 863.2. Samples: 549326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:06:13,432][00361] Avg episode reward: [(0, '12.918')] | |
| [2024-05-20 04:06:13,435][03116] Saving new best policy, reward=12.918! | |
| [2024-05-20 04:06:16,903][03129] Updated weights for policy 0, policy_version 540 (0.0024) | |
| [2024-05-20 04:06:18,432][00361] Fps is (10 sec: 3685.4, 60 sec: 3413.2, 300 sec: 3304.5). Total num frames: 2211840. Throughput: 0: 887.9. Samples: 552398. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:06:18,434][00361] Avg episode reward: [(0, '12.645')] | |
| [2024-05-20 04:06:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 2224128. Throughput: 0: 846.6. Samples: 556476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:06:23,433][00361] Avg episode reward: [(0, '12.315')] | |
| [2024-05-20 04:06:28,429][00361] Fps is (10 sec: 3277.7, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 2244608. Throughput: 0: 836.4. Samples: 561706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:06:28,432][00361] Avg episode reward: [(0, '11.503')] | |
| [2024-05-20 04:06:29,862][03129] Updated weights for policy 0, policy_version 550 (0.0014) | |
| [2024-05-20 04:06:33,429][00361] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3304.6). Total num frames: 2265088. Throughput: 0: 864.0. Samples: 564770. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:06:33,433][00361] Avg episode reward: [(0, '9.853')] | |
| [2024-05-20 04:06:38,429][00361] Fps is (10 sec: 3686.3, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2281472. Throughput: 0: 871.3. Samples: 570096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:06:38,431][00361] Avg episode reward: [(0, '9.309')] | |
| [2024-05-20 04:06:38,452][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000557_2281472.pth... | |
| [2024-05-20 04:06:38,631][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000363_1486848.pth | |
| [2024-05-20 04:06:42,770][03129] Updated weights for policy 0, policy_version 560 (0.0014) | |
| [2024-05-20 04:06:43,429][00361] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 2293760. Throughput: 0: 824.8. Samples: 574114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:06:43,432][00361] Avg episode reward: [(0, '10.236')] | |
| [2024-05-20 04:06:48,429][00361] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3304.6). Total num frames: 2314240. Throughput: 0: 840.6. Samples: 577248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:06:48,432][00361] Avg episode reward: [(0, '9.907')] | |
| [2024-05-20 04:06:52,825][03129] Updated weights for policy 0, policy_version 570 (0.0028) | |
| [2024-05-20 04:06:53,431][00361] Fps is (10 sec: 4095.2, 60 sec: 3481.5, 300 sec: 3332.3). Total num frames: 2334720. Throughput: 0: 896.5. Samples: 583466. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:06:53,438][00361] Avg episode reward: [(0, '10.957')] | |
| [2024-05-20 04:06:58,429][00361] Fps is (10 sec: 3276.7, 60 sec: 3345.0, 300 sec: 3318.4). Total num frames: 2347008. Throughput: 0: 842.7. Samples: 587246. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:06:58,432][00361] Avg episode reward: [(0, '11.838')] | |
| [2024-05-20 04:07:03,429][00361] Fps is (10 sec: 2867.7, 60 sec: 3413.5, 300 sec: 3290.7). Total num frames: 2363392. Throughput: 0: 822.5. Samples: 589410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:07:03,434][00361] Avg episode reward: [(0, '11.666')] | |
| [2024-05-20 04:07:06,289][03129] Updated weights for policy 0, policy_version 580 (0.0019) | |
| [2024-05-20 04:07:08,429][00361] Fps is (10 sec: 3276.9, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2379776. Throughput: 0: 849.9. Samples: 594720. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:07:08,432][00361] Avg episode reward: [(0, '11.540')] | |
| [2024-05-20 04:07:13,431][00361] Fps is (10 sec: 2866.6, 60 sec: 3276.7, 300 sec: 3304.5). Total num frames: 2392064. Throughput: 0: 816.5. Samples: 598448. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:07:13,438][00361] Avg episode reward: [(0, '12.660')] | |
| [2024-05-20 04:07:18,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.7, 300 sec: 3276.8). Total num frames: 2404352. Throughput: 0: 790.6. Samples: 600348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:07:18,436][00361] Avg episode reward: [(0, '12.916')] | |
| [2024-05-20 04:07:20,729][03129] Updated weights for policy 0, policy_version 590 (0.0031) | |
| [2024-05-20 04:07:23,429][00361] Fps is (10 sec: 3277.5, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 2424832. Throughput: 0: 795.1. Samples: 605876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:07:23,437][00361] Avg episode reward: [(0, '14.043')] | |
| [2024-05-20 04:07:23,443][03116] Saving new best policy, reward=14.043! | |
| [2024-05-20 04:07:28,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3304.6). Total num frames: 2445312. Throughput: 0: 838.9. Samples: 611864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:07:28,432][00361] Avg episode reward: [(0, '13.987')] | |
| [2024-05-20 04:07:32,789][03129] Updated weights for policy 0, policy_version 600 (0.0032) | |
| [2024-05-20 04:07:33,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3290.7). Total num frames: 2457600. Throughput: 0: 808.8. Samples: 613646. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:07:33,433][00361] Avg episode reward: [(0, '13.695')] | |
| [2024-05-20 04:07:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3276.8). Total num frames: 2473984. Throughput: 0: 770.2. Samples: 618122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:07:38,431][00361] Avg episode reward: [(0, '13.717')] | |
| [2024-05-20 04:07:43,429][00361] Fps is (10 sec: 3686.3, 60 sec: 3345.0, 300 sec: 3304.6). Total num frames: 2494464. Throughput: 0: 822.8. Samples: 624274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:07:43,432][00361] Avg episode reward: [(0, '12.574')] | |
| [2024-05-20 04:07:43,701][03129] Updated weights for policy 0, policy_version 610 (0.0013) | |
| [2024-05-20 04:07:48,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 2510848. Throughput: 0: 836.7. Samples: 627060. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:07:48,437][00361] Avg episode reward: [(0, '12.718')] | |
| [2024-05-20 04:07:53,429][00361] Fps is (10 sec: 2867.3, 60 sec: 3140.4, 300 sec: 3276.8). Total num frames: 2523136. Throughput: 0: 804.3. Samples: 630914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:07:53,432][00361] Avg episode reward: [(0, '13.451')] | |
| [2024-05-20 04:07:56,553][03129] Updated weights for policy 0, policy_version 620 (0.0021) | |
| [2024-05-20 04:07:58,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3290.7). Total num frames: 2543616. Throughput: 0: 849.4. Samples: 636668. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 04:07:58,437][00361] Avg episode reward: [(0, '13.162')] | |
| [2024-05-20 04:08:03,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2564096. Throughput: 0: 877.5. Samples: 639836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:03,431][00361] Avg episode reward: [(0, '13.345')] | |
| [2024-05-20 04:08:08,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 2576384. Throughput: 0: 857.2. Samples: 644450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:08:08,434][00361] Avg episode reward: [(0, '13.307')] | |
| [2024-05-20 04:08:08,674][03129] Updated weights for policy 0, policy_version 630 (0.0025) | |
| [2024-05-20 04:08:13,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3304.6). Total num frames: 2596864. Throughput: 0: 833.6. Samples: 649376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:13,434][00361] Avg episode reward: [(0, '14.106')] | |
| [2024-05-20 04:08:13,440][03116] Saving new best policy, reward=14.106! | |
| [2024-05-20 04:08:18,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3332.3). Total num frames: 2617344. Throughput: 0: 861.2. Samples: 652402. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:18,435][00361] Avg episode reward: [(0, '14.804')] | |
| [2024-05-20 04:08:18,445][03116] Saving new best policy, reward=14.804! | |
| [2024-05-20 04:08:19,230][03129] Updated weights for policy 0, policy_version 640 (0.0017) | |
| [2024-05-20 04:08:23,431][00361] Fps is (10 sec: 3685.7, 60 sec: 3481.5, 300 sec: 3346.2). Total num frames: 2633728. Throughput: 0: 886.6. Samples: 658020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:23,435][00361] Avg episode reward: [(0, '14.671')] | |
| [2024-05-20 04:08:28,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2646016. Throughput: 0: 837.3. Samples: 661952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:28,433][00361] Avg episode reward: [(0, '15.175')] | |
| [2024-05-20 04:08:28,448][03116] Saving new best policy, reward=15.175! | |
| [2024-05-20 04:08:31,824][03129] Updated weights for policy 0, policy_version 650 (0.0018) | |
| [2024-05-20 04:08:33,429][00361] Fps is (10 sec: 3277.3, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 2666496. Throughput: 0: 844.3. Samples: 665052. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:08:33,434][00361] Avg episode reward: [(0, '16.061')] | |
| [2024-05-20 04:08:33,441][03116] Saving new best policy, reward=16.061! | |
| [2024-05-20 04:08:38,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3360.1). Total num frames: 2686976. Throughput: 0: 896.1. Samples: 671238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:38,431][00361] Avg episode reward: [(0, '16.295')] | |
| [2024-05-20 04:08:38,443][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000656_2686976.pth... | |
| [2024-05-20 04:08:38,576][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000456_1867776.pth | |
| [2024-05-20 04:08:38,595][03116] Saving new best policy, reward=16.295! | |
| [2024-05-20 04:08:43,429][00361] Fps is (10 sec: 3276.9, 60 sec: 3413.4, 300 sec: 3346.2). Total num frames: 2699264. Throughput: 0: 859.3. Samples: 675338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:43,432][00361] Avg episode reward: [(0, '16.482')] | |
| [2024-05-20 04:08:43,438][03116] Saving new best policy, reward=16.482! | |
| [2024-05-20 04:08:44,387][03129] Updated weights for policy 0, policy_version 660 (0.0028) | |
| [2024-05-20 04:08:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2715648. Throughput: 0: 833.8. Samples: 677356. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:08:48,432][00361] Avg episode reward: [(0, '18.133')] | |
| [2024-05-20 04:08:48,442][03116] Saving new best policy, reward=18.133! | |
| [2024-05-20 04:08:53,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3374.0). Total num frames: 2736128. Throughput: 0: 869.1. Samples: 683558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:08:53,437][00361] Avg episode reward: [(0, '18.628')] | |
| [2024-05-20 04:08:53,440][03116] Saving new best policy, reward=18.628! | |
| [2024-05-20 04:08:54,800][03129] Updated weights for policy 0, policy_version 670 (0.0024) | |
| [2024-05-20 04:08:58,430][00361] Fps is (10 sec: 3686.2, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 2752512. Throughput: 0: 878.0. Samples: 688888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:08:58,432][00361] Avg episode reward: [(0, '19.397')] | |
| [2024-05-20 04:08:58,452][03116] Saving new best policy, reward=19.397! | |
| [2024-05-20 04:09:03,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2764800. Throughput: 0: 852.0. Samples: 690744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:09:03,432][00361] Avg episode reward: [(0, '19.076')] | |
| [2024-05-20 04:09:07,474][03129] Updated weights for policy 0, policy_version 680 (0.0039) | |
| [2024-05-20 04:09:08,429][00361] Fps is (10 sec: 3277.0, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 2785280. Throughput: 0: 845.3. Samples: 696056. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:09:08,436][00361] Avg episode reward: [(0, '19.902')] | |
| [2024-05-20 04:09:08,472][03116] Saving new best policy, reward=19.902! | |
| [2024-05-20 04:09:13,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2805760. Throughput: 0: 897.6. Samples: 702346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:09:13,433][00361] Avg episode reward: [(0, '20.793')] | |
| [2024-05-20 04:09:13,443][03116] Saving new best policy, reward=20.793! | |
| [2024-05-20 04:09:18,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 2818048. Throughput: 0: 873.5. Samples: 704358. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:09:18,434][00361] Avg episode reward: [(0, '19.869')] | |
| [2024-05-20 04:09:20,429][03129] Updated weights for policy 0, policy_version 690 (0.0025) | |
| [2024-05-20 04:09:23,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3387.9). Total num frames: 2838528. Throughput: 0: 830.0. Samples: 708588. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:09:23,436][00361] Avg episode reward: [(0, '19.678')] | |
| [2024-05-20 04:09:28,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3401.8). Total num frames: 2859008. Throughput: 0: 877.5. Samples: 714826. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:09:28,431][00361] Avg episode reward: [(0, '20.700')] | |
| [2024-05-20 04:09:30,128][03129] Updated weights for policy 0, policy_version 700 (0.0015) | |
| [2024-05-20 04:09:33,431][00361] Fps is (10 sec: 3685.8, 60 sec: 3481.5, 300 sec: 3415.6). Total num frames: 2875392. Throughput: 0: 903.7. Samples: 718024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:09:33,433][00361] Avg episode reward: [(0, '21.086')] | |
| [2024-05-20 04:09:33,435][03116] Saving new best policy, reward=21.086! | |
| [2024-05-20 04:09:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 2887680. Throughput: 0: 849.8. Samples: 721798. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:09:38,436][00361] Avg episode reward: [(0, '20.702')] | |
| [2024-05-20 04:09:42,863][03129] Updated weights for policy 0, policy_version 710 (0.0020) | |
| [2024-05-20 04:09:43,429][00361] Fps is (10 sec: 3277.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2908160. Throughput: 0: 861.6. Samples: 727658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:09:43,436][00361] Avg episode reward: [(0, '20.795')] | |
| [2024-05-20 04:09:48,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3429.5). Total num frames: 2928640. Throughput: 0: 888.5. Samples: 730728. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:09:48,432][00361] Avg episode reward: [(0, '21.475')] | |
| [2024-05-20 04:09:48,442][03116] Saving new best policy, reward=21.475! | |
| [2024-05-20 04:09:53,432][00361] Fps is (10 sec: 3276.0, 60 sec: 3413.2, 300 sec: 3415.6). Total num frames: 2940928. Throughput: 0: 877.9. Samples: 735562. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:09:53,437][00361] Avg episode reward: [(0, '22.826')] | |
| [2024-05-20 04:09:53,440][03116] Saving new best policy, reward=22.826! | |
| [2024-05-20 04:09:55,416][03129] Updated weights for policy 0, policy_version 720 (0.0024) | |
| [2024-05-20 04:09:58,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3387.9). Total num frames: 2957312. Throughput: 0: 838.7. Samples: 740086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:09:58,434][00361] Avg episode reward: [(0, '22.361')] | |
| [2024-05-20 04:10:03,436][00361] Fps is (10 sec: 3684.8, 60 sec: 3549.5, 300 sec: 3401.7). Total num frames: 2977792. Throughput: 0: 863.8. Samples: 743236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:10:03,440][00361] Avg episode reward: [(0, '22.047')] | |
| [2024-05-20 04:10:05,558][03129] Updated weights for policy 0, policy_version 730 (0.0022) | |
| [2024-05-20 04:10:08,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 2994176. Throughput: 0: 902.7. Samples: 749208. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:10:08,432][00361] Avg episode reward: [(0, '22.247')] | |
| [2024-05-20 04:10:13,429][00361] Fps is (10 sec: 3279.0, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3010560. Throughput: 0: 847.7. Samples: 752974. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:10:13,432][00361] Avg episode reward: [(0, '22.933')] | |
| [2024-05-20 04:10:13,440][03116] Saving new best policy, reward=22.933! | |
| [2024-05-20 04:10:18,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3026944. Throughput: 0: 839.8. Samples: 755814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:10:18,436][00361] Avg episode reward: [(0, '22.150')] | |
| [2024-05-20 04:10:18,511][03129] Updated weights for policy 0, policy_version 740 (0.0031) | |
| [2024-05-20 04:10:23,431][00361] Fps is (10 sec: 3276.2, 60 sec: 3413.2, 300 sec: 3401.7). Total num frames: 3043328. Throughput: 0: 854.9. Samples: 760268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:10:23,433][00361] Avg episode reward: [(0, '21.528')] | |
| [2024-05-20 04:10:28,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 3055616. Throughput: 0: 811.9. Samples: 764192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:10:28,437][00361] Avg episode reward: [(0, '20.723')] | |
| [2024-05-20 04:10:33,235][03129] Updated weights for policy 0, policy_version 750 (0.0029) | |
| [2024-05-20 04:10:33,429][00361] Fps is (10 sec: 2867.7, 60 sec: 3276.9, 300 sec: 3374.0). Total num frames: 3072000. Throughput: 0: 787.6. Samples: 766172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:10:33,436][00361] Avg episode reward: [(0, '21.575')] | |
| [2024-05-20 04:10:38,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3092480. Throughput: 0: 817.3. Samples: 772338. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:10:38,437][00361] Avg episode reward: [(0, '20.518')] | |
| [2024-05-20 04:10:38,450][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000755_3092480.pth... | |
| [2024-05-20 04:10:38,595][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000557_2281472.pth | |
| [2024-05-20 04:10:43,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 3108864. Throughput: 0: 840.0. Samples: 777886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:10:43,440][00361] Avg episode reward: [(0, '19.985')] | |
| [2024-05-20 04:10:44,308][03129] Updated weights for policy 0, policy_version 760 (0.0042) | |
| [2024-05-20 04:10:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 3121152. Throughput: 0: 812.5. Samples: 779792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:10:48,433][00361] Avg episode reward: [(0, '21.446')] | |
| [2024-05-20 04:10:53,431][00361] Fps is (10 sec: 3276.1, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 3141632. Throughput: 0: 794.2. Samples: 784948. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:10:53,439][00361] Avg episode reward: [(0, '22.140')] | |
| [2024-05-20 04:10:55,669][03129] Updated weights for policy 0, policy_version 770 (0.0014) | |
| [2024-05-20 04:10:58,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3162112. Throughput: 0: 846.8. Samples: 791082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:10:58,431][00361] Avg episode reward: [(0, '21.889')] | |
| [2024-05-20 04:11:03,437][00361] Fps is (10 sec: 3684.3, 60 sec: 3345.0, 300 sec: 3401.7). Total num frames: 3178496. Throughput: 0: 835.2. Samples: 793406. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:11:03,439][00361] Avg episode reward: [(0, '21.665')] | |
| [2024-05-20 04:11:08,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 3190784. Throughput: 0: 827.7. Samples: 797514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:11:08,431][00361] Avg episode reward: [(0, '21.551')] | |
| [2024-05-20 04:11:08,527][03129] Updated weights for policy 0, policy_version 780 (0.0021) | |
| [2024-05-20 04:11:13,429][00361] Fps is (10 sec: 3689.3, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3215360. Throughput: 0: 878.6. Samples: 803728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:11:13,435][00361] Avg episode reward: [(0, '22.103')] | |
| [2024-05-20 04:11:18,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3231744. Throughput: 0: 903.7. Samples: 806838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:11:18,435][00361] Avg episode reward: [(0, '21.935')] | |
| [2024-05-20 04:11:19,687][03129] Updated weights for policy 0, policy_version 790 (0.0031) | |
| [2024-05-20 04:11:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.2, 300 sec: 3387.9). Total num frames: 3244032. Throughput: 0: 856.0. Samples: 810860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:11:23,434][00361] Avg episode reward: [(0, '22.095')] | |
| [2024-05-20 04:11:28,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3264512. Throughput: 0: 852.8. Samples: 816260. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:11:28,432][00361] Avg episode reward: [(0, '24.271')] | |
| [2024-05-20 04:11:28,443][03116] Saving new best policy, reward=24.271! | |
| [2024-05-20 04:11:31,310][03129] Updated weights for policy 0, policy_version 800 (0.0047) | |
| [2024-05-20 04:11:33,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3401.8). Total num frames: 3284992. Throughput: 0: 879.0. Samples: 819346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:11:33,437][00361] Avg episode reward: [(0, '24.405')] | |
| [2024-05-20 04:11:33,440][03116] Saving new best policy, reward=24.405! | |
| [2024-05-20 04:11:38,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3297280. Throughput: 0: 876.7. Samples: 824396. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:11:38,434][00361] Avg episode reward: [(0, '25.021')] | |
| [2024-05-20 04:11:38,441][03116] Saving new best policy, reward=25.021! | |
| [2024-05-20 04:11:43,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3313664. Throughput: 0: 836.7. Samples: 828732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:11:43,436][00361] Avg episode reward: [(0, '25.549')] | |
| [2024-05-20 04:11:43,442][03116] Saving new best policy, reward=25.549! | |
| [2024-05-20 04:11:44,070][03129] Updated weights for policy 0, policy_version 810 (0.0019) | |
| [2024-05-20 04:11:48,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3387.9). Total num frames: 3334144. Throughput: 0: 852.5. Samples: 831764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:11:48,436][00361] Avg episode reward: [(0, '25.154')] | |
| [2024-05-20 04:11:53,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3401.8). Total num frames: 3350528. Throughput: 0: 895.2. Samples: 837796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:11:53,431][00361] Avg episode reward: [(0, '25.154')] | |
| [2024-05-20 04:11:55,598][03129] Updated weights for policy 0, policy_version 820 (0.0024) | |
| [2024-05-20 04:11:58,430][00361] Fps is (10 sec: 2867.0, 60 sec: 3345.0, 300 sec: 3387.9). Total num frames: 3362816. Throughput: 0: 842.6. Samples: 841644. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:11:58,435][00361] Avg episode reward: [(0, '24.167')] | |
| [2024-05-20 04:12:03,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.5, 300 sec: 3387.9). Total num frames: 3379200. Throughput: 0: 812.7. Samples: 843410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:03,437][00361] Avg episode reward: [(0, '24.139')] | |
| [2024-05-20 04:12:07,599][03129] Updated weights for policy 0, policy_version 830 (0.0022) | |
| [2024-05-20 04:12:08,429][00361] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3415.7). Total num frames: 3399680. Throughput: 0: 862.7. Samples: 849682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:08,438][00361] Avg episode reward: [(0, '23.850')] | |
| [2024-05-20 04:12:13,434][00361] Fps is (10 sec: 3684.6, 60 sec: 3344.8, 300 sec: 3429.5). Total num frames: 3416064. Throughput: 0: 849.7. Samples: 854500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:13,436][00361] Avg episode reward: [(0, '23.655')] | |
| [2024-05-20 04:12:18,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 3428352. Throughput: 0: 821.6. Samples: 856316. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:12:18,436][00361] Avg episode reward: [(0, '24.371')] | |
| [2024-05-20 04:12:20,601][03129] Updated weights for policy 0, policy_version 840 (0.0031) | |
| [2024-05-20 04:12:23,429][00361] Fps is (10 sec: 3278.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3448832. Throughput: 0: 836.1. Samples: 862020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:23,431][00361] Avg episode reward: [(0, '24.599')] | |
| [2024-05-20 04:12:28,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 3469312. Throughput: 0: 873.7. Samples: 868048. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:12:28,434][00361] Avg episode reward: [(0, '24.988')] | |
| [2024-05-20 04:12:32,712][03129] Updated weights for policy 0, policy_version 850 (0.0031) | |
| [2024-05-20 04:12:33,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3415.6). Total num frames: 3481600. Throughput: 0: 846.4. Samples: 869854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:33,434][00361] Avg episode reward: [(0, '24.368')] | |
| [2024-05-20 04:12:38,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 3497984. Throughput: 0: 809.6. Samples: 874228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:38,431][00361] Avg episode reward: [(0, '24.395')] | |
| [2024-05-20 04:12:38,443][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000854_3497984.pth... | |
| [2024-05-20 04:12:38,577][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000656_2686976.pth | |
| [2024-05-20 04:12:43,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3518464. Throughput: 0: 849.1. Samples: 879852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:12:43,434][00361] Avg episode reward: [(0, '23.770')] | |
| [2024-05-20 04:12:44,211][03129] Updated weights for policy 0, policy_version 860 (0.0034) | |
| [2024-05-20 04:12:48,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3415.6). Total num frames: 3530752. Throughput: 0: 865.5. Samples: 882356. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:12:48,433][00361] Avg episode reward: [(0, '22.779')] | |
| [2024-05-20 04:12:53,429][00361] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3387.9). Total num frames: 3543040. Throughput: 0: 802.0. Samples: 885770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:12:53,432][00361] Avg episode reward: [(0, '22.758')] | |
| [2024-05-20 04:12:58,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 3559424. Throughput: 0: 811.6. Samples: 891020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:12:58,432][00361] Avg episode reward: [(0, '23.493')] | |
| [2024-05-20 04:12:58,454][03129] Updated weights for policy 0, policy_version 870 (0.0023) | |
| [2024-05-20 04:13:03,431][00361] Fps is (10 sec: 3685.8, 60 sec: 3345.0, 300 sec: 3401.7). Total num frames: 3579904. Throughput: 0: 832.7. Samples: 893788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:13:03,436][00361] Avg episode reward: [(0, '21.972')] | |
| [2024-05-20 04:13:08,433][00361] Fps is (10 sec: 3684.8, 60 sec: 3276.6, 300 sec: 3387.8). Total num frames: 3596288. Throughput: 0: 813.1. Samples: 898612. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:13:08,438][00361] Avg episode reward: [(0, '23.646')] | |
| [2024-05-20 04:13:11,387][03129] Updated weights for policy 0, policy_version 880 (0.0037) | |
| [2024-05-20 04:13:13,429][00361] Fps is (10 sec: 3277.4, 60 sec: 3277.1, 300 sec: 3374.0). Total num frames: 3612672. Throughput: 0: 781.6. Samples: 903220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:13:13,437][00361] Avg episode reward: [(0, '24.114')] | |
| [2024-05-20 04:13:18,429][00361] Fps is (10 sec: 3688.0, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3633152. Throughput: 0: 811.8. Samples: 906384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:13:18,432][00361] Avg episode reward: [(0, '24.424')] | |
| [2024-05-20 04:13:21,150][03129] Updated weights for policy 0, policy_version 890 (0.0033) | |
| [2024-05-20 04:13:23,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 3649536. Throughput: 0: 848.5. Samples: 912412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:13:23,435][00361] Avg episode reward: [(0, '24.402')] | |
| [2024-05-20 04:13:28,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 3661824. Throughput: 0: 808.0. Samples: 916210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:13:28,434][00361] Avg episode reward: [(0, '25.067')] | |
| [2024-05-20 04:13:33,430][00361] Fps is (10 sec: 2867.0, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3678208. Throughput: 0: 810.0. Samples: 918808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-05-20 04:13:33,440][00361] Avg episode reward: [(0, '25.347')] | |
| [2024-05-20 04:13:36,006][03129] Updated weights for policy 0, policy_version 900 (0.0056) | |
| [2024-05-20 04:13:38,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 3694592. Throughput: 0: 827.2. Samples: 922994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:13:38,434][00361] Avg episode reward: [(0, '26.332')] | |
| [2024-05-20 04:13:38,444][03116] Saving new best policy, reward=26.332! | |
| [2024-05-20 04:13:43,429][00361] Fps is (10 sec: 2867.4, 60 sec: 3140.3, 300 sec: 3360.1). Total num frames: 3706880. Throughput: 0: 814.3. Samples: 927662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:13:43,435][00361] Avg episode reward: [(0, '24.896')] | |
| [2024-05-20 04:13:48,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 3723264. Throughput: 0: 796.6. Samples: 929632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:13:48,438][00361] Avg episode reward: [(0, '24.840')] | |
| [2024-05-20 04:13:48,744][03129] Updated weights for policy 0, policy_version 910 (0.0028) | |
| [2024-05-20 04:13:53,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 3743744. Throughput: 0: 821.3. Samples: 935566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:13:53,432][00361] Avg episode reward: [(0, '24.918')] | |
| [2024-05-20 04:13:58,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3764224. Throughput: 0: 850.8. Samples: 941506. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:13:58,434][00361] Avg episode reward: [(0, '22.079')] | |
| [2024-05-20 04:13:59,634][03129] Updated weights for policy 0, policy_version 920 (0.0018) | |
| [2024-05-20 04:14:03,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.9, 300 sec: 3360.1). Total num frames: 3776512. Throughput: 0: 820.0. Samples: 943282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-05-20 04:14:03,432][00361] Avg episode reward: [(0, '21.866')] | |
| [2024-05-20 04:14:08,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3345.3, 300 sec: 3360.1). Total num frames: 3796992. Throughput: 0: 795.8. Samples: 948222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:14:08,437][00361] Avg episode reward: [(0, '21.163')] | |
| [2024-05-20 04:14:11,257][03129] Updated weights for policy 0, policy_version 930 (0.0014) | |
| [2024-05-20 04:14:13,429][00361] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 3817472. Throughput: 0: 850.6. Samples: 954486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:14:13,437][00361] Avg episode reward: [(0, '19.910')] | |
| [2024-05-20 04:14:18,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3360.1). Total num frames: 3829760. Throughput: 0: 846.8. Samples: 956912. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-05-20 04:14:18,431][00361] Avg episode reward: [(0, '19.281')] | |
| [2024-05-20 04:14:23,429][00361] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3346.2). Total num frames: 3846144. Throughput: 0: 840.4. Samples: 960814. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-05-20 04:14:23,436][00361] Avg episode reward: [(0, '19.799')] | |
| [2024-05-20 04:14:24,209][03129] Updated weights for policy 0, policy_version 940 (0.0026) | |
| [2024-05-20 04:14:28,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 3866624. Throughput: 0: 877.1. Samples: 967132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:14:28,437][00361] Avg episode reward: [(0, '22.079')] | |
| [2024-05-20 04:14:33,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3374.0). Total num frames: 3883008. Throughput: 0: 900.1. Samples: 970136. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-05-20 04:14:33,432][00361] Avg episode reward: [(0, '23.497')] | |
| [2024-05-20 04:14:35,378][03129] Updated weights for policy 0, policy_version 950 (0.0018) | |
| [2024-05-20 04:14:38,432][00361] Fps is (10 sec: 2866.4, 60 sec: 3344.9, 300 sec: 3346.2). Total num frames: 3895296. Throughput: 0: 860.3. Samples: 974282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:14:38,434][00361] Avg episode reward: [(0, '23.788')] | |
| [2024-05-20 04:14:38,455][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000951_3895296.pth... | |
| [2024-05-20 04:14:38,620][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000755_3092480.pth | |
| [2024-05-20 04:14:43,429][00361] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 3915776. Throughput: 0: 844.7. Samples: 979516. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:14:43,437][00361] Avg episode reward: [(0, '24.403')] | |
| [2024-05-20 04:14:46,798][03129] Updated weights for policy 0, policy_version 960 (0.0030) | |
| [2024-05-20 04:14:48,429][00361] Fps is (10 sec: 4097.2, 60 sec: 3549.9, 300 sec: 3374.0). Total num frames: 3936256. Throughput: 0: 874.4. Samples: 982632. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-05-20 04:14:48,436][00361] Avg episode reward: [(0, '25.375')] | |
| [2024-05-20 04:14:53,429][00361] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 3952640. Throughput: 0: 880.8. Samples: 987858. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-05-20 04:14:53,434][00361] Avg episode reward: [(0, '25.206')] | |
| [2024-05-20 04:14:58,429][00361] Fps is (10 sec: 2867.1, 60 sec: 3345.0, 300 sec: 3346.3). Total num frames: 3964928. Throughput: 0: 835.2. Samples: 992072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-05-20 04:14:58,431][00361] Avg episode reward: [(0, '23.940')] | |
| [2024-05-20 04:14:59,692][03129] Updated weights for policy 0, policy_version 970 (0.0035) | |
| [2024-05-20 04:15:03,429][00361] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3985408. Throughput: 0: 845.7. Samples: 994968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-05-20 04:15:03,435][00361] Avg episode reward: [(0, '22.089')] | |
| [2024-05-20 04:15:08,013][03116] Stopping Batcher_0... | |
| [2024-05-20 04:15:08,014][03116] Loop batcher_evt_loop terminating... | |
| [2024-05-20 04:15:08,014][00361] Component Batcher_0 stopped! | |
| [2024-05-20 04:15:08,021][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-05-20 04:15:08,153][03129] Weights refcount: 2 0 | |
| [2024-05-20 04:15:08,158][00361] Component RolloutWorker_w7 stopped! | |
| [2024-05-20 04:15:08,160][03136] Stopping RolloutWorker_w7... | |
| [2024-05-20 04:15:08,167][03129] Stopping InferenceWorker_p0-w0... | |
| [2024-05-20 04:15:08,167][03129] Loop inference_proc0-0_evt_loop terminating... | |
| [2024-05-20 04:15:08,167][00361] Component InferenceWorker_p0-w0 stopped! | |
| [2024-05-20 04:15:08,175][03136] Loop rollout_proc7_evt_loop terminating... | |
| [2024-05-20 04:15:08,183][00361] Component RolloutWorker_w5 stopped! | |
| [2024-05-20 04:15:08,185][03135] Stopping RolloutWorker_w5... | |
| [2024-05-20 04:15:08,186][03135] Loop rollout_proc5_evt_loop terminating... | |
| [2024-05-20 04:15:08,193][00361] Component RolloutWorker_w3 stopped! | |
| [2024-05-20 04:15:08,196][03133] Stopping RolloutWorker_w3... | |
| [2024-05-20 04:15:08,199][03133] Loop rollout_proc3_evt_loop terminating... | |
| [2024-05-20 04:15:08,215][00361] Component RolloutWorker_w1 stopped! | |
| [2024-05-20 04:15:08,218][03132] Stopping RolloutWorker_w1... | |
| [2024-05-20 04:15:08,239][03131] Stopping RolloutWorker_w2... | |
| [2024-05-20 04:15:08,240][03131] Loop rollout_proc2_evt_loop terminating... | |
| [2024-05-20 04:15:08,239][00361] Component RolloutWorker_w2 stopped! | |
| [2024-05-20 04:15:08,247][03137] Stopping RolloutWorker_w6... | |
| [2024-05-20 04:15:08,248][03137] Loop rollout_proc6_evt_loop terminating... | |
| [2024-05-20 04:15:08,248][00361] Component RolloutWorker_w6 stopped! | |
| [2024-05-20 04:15:08,222][03132] Loop rollout_proc1_evt_loop terminating... | |
| [2024-05-20 04:15:08,251][00361] Component RolloutWorker_w0 stopped! | |
| [2024-05-20 04:15:08,251][03130] Stopping RolloutWorker_w0... | |
| [2024-05-20 04:15:08,265][03130] Loop rollout_proc0_evt_loop terminating... | |
| [2024-05-20 04:15:08,280][03116] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000854_3497984.pth | |
| [2024-05-20 04:15:08,298][03116] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-05-20 04:15:08,300][03134] Stopping RolloutWorker_w4... | |
| [2024-05-20 04:15:08,300][00361] Component RolloutWorker_w4 stopped! | |
| [2024-05-20 04:15:08,318][03134] Loop rollout_proc4_evt_loop terminating... | |
| [2024-05-20 04:15:08,538][03116] Stopping LearnerWorker_p0... | |
| [2024-05-20 04:15:08,538][00361] Component LearnerWorker_p0 stopped! | |
| [2024-05-20 04:15:08,540][00361] Waiting for process learner_proc0 to stop... | |
| [2024-05-20 04:15:08,561][03116] Loop learner_proc0_evt_loop terminating... | |
| [2024-05-20 04:15:11,079][00361] Waiting for process inference_proc0-0 to join... | |
| [2024-05-20 04:15:11,087][00361] Waiting for process rollout_proc0 to join... | |
| [2024-05-20 04:15:13,106][00361] Waiting for process rollout_proc1 to join... | |
| [2024-05-20 04:15:13,145][00361] Waiting for process rollout_proc2 to join... | |
| [2024-05-20 04:15:13,150][00361] Waiting for process rollout_proc3 to join... | |
| [2024-05-20 04:15:13,157][00361] Waiting for process rollout_proc4 to join... | |
| [2024-05-20 04:15:13,160][00361] Waiting for process rollout_proc5 to join... | |
| [2024-05-20 04:15:13,165][00361] Waiting for process rollout_proc6 to join... | |
| [2024-05-20 04:15:13,168][00361] Waiting for process rollout_proc7 to join... | |
| [2024-05-20 04:15:13,173][00361] Batcher 0 profile tree view: | |
| batching: 27.8886, releasing_batches: 0.0312 | |
| [2024-05-20 04:15:13,175][00361] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0094 | |
| wait_policy_total: 497.9666 | |
| update_model: 9.2479 | |
| weight_update: 0.0020 | |
| one_step: 0.0080 | |
| handle_policy_step: 647.4900 | |
| deserialize: 17.5959, stack: 3.4310, obs_to_device_normalize: 128.4989, forward: 348.3492, send_messages: 31.6057 | |
| prepare_outputs: 85.5106 | |
| to_cpu: 49.1826 | |
| [2024-05-20 04:15:13,177][00361] Learner 0 profile tree view: | |
| misc: 0.0102, prepare_batch: 13.3017 | |
| train: 76.2725 | |
| epoch_init: 0.0069, minibatch_init: 0.0078, losses_postprocess: 0.6398, kl_divergence: 0.7492, after_optimizer: 34.3880 | |
| calculate_losses: 27.6178 | |
| losses_init: 0.0060, forward_head: 1.4231, bptt_initial: 18.3238, tail: 1.1888, advantages_returns: 0.2513, losses: 3.9009 | |
| bptt: 2.1888 | |
| bptt_forward_core: 2.0967 | |
| update: 12.1485 | |
| clip: 1.0419 | |
| [2024-05-20 04:15:13,179][00361] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.2518, enqueue_policy_requests: 139.2630, env_step: 925.8525, overhead: 17.4375, complete_rollouts: 7.6678 | |
| save_policy_outputs: 22.3893 | |
| split_output_tensors: 9.0486 | |
| [2024-05-20 04:15:13,180][00361] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3814, enqueue_policy_requests: 137.3472, env_step: 919.1039, overhead: 17.5783, complete_rollouts: 7.2374 | |
| save_policy_outputs: 22.0811 | |
| split_output_tensors: 9.0731 | |
| [2024-05-20 04:15:13,185][00361] Loop Runner_EvtLoop terminating... | |
| [2024-05-20 04:15:13,187][00361] Runner profile tree view: | |
| main_loop: 1227.8436 | |
| [2024-05-20 04:15:13,191][00361] Collected {0: 4005888}, FPS: 3262.5 | |
| [2024-05-20 04:15:13,599][00361] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-05-20 04:15:13,601][00361] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-05-20 04:15:13,603][00361] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-05-20 04:15:13,605][00361] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-05-20 04:15:13,607][00361] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-05-20 04:15:13,610][00361] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-05-20 04:15:13,611][00361] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-05-20 04:15:13,612][00361] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-05-20 04:15:13,614][00361] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2024-05-20 04:15:13,615][00361] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2024-05-20 04:15:13,616][00361] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-05-20 04:15:13,617][00361] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-05-20 04:15:13,618][00361] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-05-20 04:15:13,620][00361] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-05-20 04:15:13,621][00361] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-05-20 04:15:13,660][00361] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-05-20 04:15:13,664][00361] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-05-20 04:15:13,665][00361] RunningMeanStd input shape: (1,) | |
| [2024-05-20 04:15:13,683][00361] ConvEncoder: input_channels=3 | |
| [2024-05-20 04:15:13,792][00361] Conv encoder output size: 512 | |
| [2024-05-20 04:15:13,794][00361] Policy head output size: 512 | |
| [2024-05-20 04:15:14,086][00361] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-05-20 04:15:14,884][00361] Num frames 100... | |
| [2024-05-20 04:15:15,027][00361] Num frames 200... | |
| [2024-05-20 04:15:15,167][00361] Num frames 300... | |
| [2024-05-20 04:15:15,302][00361] Num frames 400... | |
| [2024-05-20 04:15:15,452][00361] Num frames 500... | |
| [2024-05-20 04:15:15,605][00361] Num frames 600... | |
| [2024-05-20 04:15:15,752][00361] Num frames 700... | |
| [2024-05-20 04:15:15,898][00361] Num frames 800... | |
| [2024-05-20 04:15:16,036][00361] Num frames 900... | |
| [2024-05-20 04:15:16,178][00361] Num frames 1000... | |
| [2024-05-20 04:15:16,315][00361] Num frames 1100... | |
| [2024-05-20 04:15:16,454][00361] Num frames 1200... | |
| [2024-05-20 04:15:16,594][00361] Num frames 1300... | |
| [2024-05-20 04:15:16,733][00361] Num frames 1400... | |
| [2024-05-20 04:15:16,875][00361] Num frames 1500... | |
| [2024-05-20 04:15:17,010][00361] Num frames 1600... | |
| [2024-05-20 04:15:17,075][00361] Avg episode rewards: #0: 39.050, true rewards: #0: 16.050 | |
| [2024-05-20 04:15:17,079][00361] Avg episode reward: 39.050, avg true_objective: 16.050 | |
| [2024-05-20 04:15:17,203][00361] Num frames 1700... | |
| [2024-05-20 04:15:17,340][00361] Num frames 1800... | |
| [2024-05-20 04:15:17,474][00361] Num frames 1900... | |
| [2024-05-20 04:15:17,616][00361] Num frames 2000... | |
| [2024-05-20 04:15:17,756][00361] Num frames 2100... | |
| [2024-05-20 04:15:17,886][00361] Num frames 2200... | |
| [2024-05-20 04:15:18,022][00361] Num frames 2300... | |
| [2024-05-20 04:15:18,162][00361] Num frames 2400... | |
| [2024-05-20 04:15:18,295][00361] Num frames 2500... | |
| [2024-05-20 04:15:18,426][00361] Num frames 2600... | |
| [2024-05-20 04:15:18,568][00361] Num frames 2700... | |
| [2024-05-20 04:15:18,702][00361] Num frames 2800... | |
| [2024-05-20 04:15:18,838][00361] Num frames 2900... | |
| [2024-05-20 04:15:18,979][00361] Num frames 3000... | |
| [2024-05-20 04:15:19,119][00361] Num frames 3100... | |
| [2024-05-20 04:15:19,255][00361] Num frames 3200... | |
| [2024-05-20 04:15:19,390][00361] Num frames 3300... | |
| [2024-05-20 04:15:19,527][00361] Num frames 3400... | |
| [2024-05-20 04:15:19,690][00361] Avg episode rewards: #0: 47.359, true rewards: #0: 17.360 | |
| [2024-05-20 04:15:19,691][00361] Avg episode reward: 47.359, avg true_objective: 17.360 | |
| [2024-05-20 04:15:19,733][00361] Num frames 3500... | |
| [2024-05-20 04:15:19,874][00361] Num frames 3600... | |
| [2024-05-20 04:15:20,008][00361] Num frames 3700... | |
| [2024-05-20 04:15:20,140][00361] Num frames 3800... | |
| [2024-05-20 04:15:20,271][00361] Num frames 3900... | |
| [2024-05-20 04:15:20,404][00361] Num frames 4000... | |
| [2024-05-20 04:15:20,540][00361] Num frames 4100... | |
| [2024-05-20 04:15:20,683][00361] Num frames 4200... | |
| [2024-05-20 04:15:20,818][00361] Num frames 4300... | |
| [2024-05-20 04:15:20,997][00361] Avg episode rewards: #0: 38.636, true rewards: #0: 14.637 | |
| [2024-05-20 04:15:20,999][00361] Avg episode reward: 38.636, avg true_objective: 14.637 | |
| [2024-05-20 04:15:21,018][00361] Num frames 4400... | |
| [2024-05-20 04:15:21,151][00361] Num frames 4500... | |
| [2024-05-20 04:15:21,287][00361] Num frames 4600... | |
| [2024-05-20 04:15:21,428][00361] Num frames 4700... | |
| [2024-05-20 04:15:21,567][00361] Num frames 4800... | |
| [2024-05-20 04:15:21,728][00361] Num frames 4900... | |
| [2024-05-20 04:15:21,929][00361] Num frames 5000... | |
| [2024-05-20 04:15:22,132][00361] Num frames 5100... | |
| [2024-05-20 04:15:22,325][00361] Num frames 5200... | |
| [2024-05-20 04:15:22,515][00361] Num frames 5300... | |
| [2024-05-20 04:15:22,739][00361] Avg episode rewards: #0: 34.457, true rewards: #0: 13.457 | |
| [2024-05-20 04:15:22,741][00361] Avg episode reward: 34.457, avg true_objective: 13.457 | |
| [2024-05-20 04:15:22,780][00361] Num frames 5400... | |
| [2024-05-20 04:15:22,980][00361] Num frames 5500... | |
| [2024-05-20 04:15:23,171][00361] Num frames 5600... | |
| [2024-05-20 04:15:23,366][00361] Num frames 5700... | |
| [2024-05-20 04:15:23,558][00361] Num frames 5800... | |
| [2024-05-20 04:15:23,766][00361] Num frames 5900... | |
| [2024-05-20 04:15:23,961][00361] Num frames 6000... | |
| [2024-05-20 04:15:24,174][00361] Num frames 6100... | |
| [2024-05-20 04:15:24,343][00361] Avg episode rewards: #0: 30.702, true rewards: #0: 12.302 | |
| [2024-05-20 04:15:24,345][00361] Avg episode reward: 30.702, avg true_objective: 12.302 | |
| [2024-05-20 04:15:24,445][00361] Num frames 6200... | |
| [2024-05-20 04:15:24,580][00361] Num frames 6300... | |
| [2024-05-20 04:15:24,719][00361] Num frames 6400... | |
| [2024-05-20 04:15:24,854][00361] Num frames 6500... | |
| [2024-05-20 04:15:24,994][00361] Num frames 6600... | |
| [2024-05-20 04:15:25,123][00361] Num frames 6700... | |
| [2024-05-20 04:15:25,262][00361] Num frames 6800... | |
| [2024-05-20 04:15:25,403][00361] Num frames 6900... | |
| [2024-05-20 04:15:25,540][00361] Num frames 7000... | |
| [2024-05-20 04:15:25,677][00361] Num frames 7100... | |
| [2024-05-20 04:15:25,838][00361] Num frames 7200... | |
| [2024-05-20 04:15:25,978][00361] Num frames 7300... | |
| [2024-05-20 04:15:26,114][00361] Num frames 7400... | |
| [2024-05-20 04:15:26,252][00361] Num frames 7500... | |
| [2024-05-20 04:15:26,406][00361] Avg episode rewards: #0: 31.622, true rewards: #0: 12.622 | |
| [2024-05-20 04:15:26,407][00361] Avg episode reward: 31.622, avg true_objective: 12.622 | |
| [2024-05-20 04:15:26,449][00361] Num frames 7600... | |
| [2024-05-20 04:15:26,580][00361] Num frames 7700... | |
| [2024-05-20 04:15:26,718][00361] Num frames 7800... | |
| [2024-05-20 04:15:26,857][00361] Num frames 7900... | |
| [2024-05-20 04:15:27,038][00361] Avg episode rewards: #0: 27.984, true rewards: #0: 11.413 | |
| [2024-05-20 04:15:27,039][00361] Avg episode reward: 27.984, avg true_objective: 11.413 | |
| [2024-05-20 04:15:27,058][00361] Num frames 8000... | |
| [2024-05-20 04:15:27,186][00361] Num frames 8100... | |
| [2024-05-20 04:15:27,321][00361] Num frames 8200... | |
| [2024-05-20 04:15:27,448][00361] Num frames 8300... | |
| [2024-05-20 04:15:27,591][00361] Num frames 8400... | |
| [2024-05-20 04:15:27,722][00361] Num frames 8500... | |
| [2024-05-20 04:15:27,860][00361] Num frames 8600... | |
| [2024-05-20 04:15:28,001][00361] Num frames 8700... | |
| [2024-05-20 04:15:28,135][00361] Num frames 8800... | |
| [2024-05-20 04:15:28,271][00361] Num frames 8900... | |
| [2024-05-20 04:15:28,393][00361] Avg episode rewards: #0: 27.061, true rewards: #0: 11.186 | |
| [2024-05-20 04:15:28,394][00361] Avg episode reward: 27.061, avg true_objective: 11.186 | |
| [2024-05-20 04:15:28,463][00361] Num frames 9000... | |
| [2024-05-20 04:15:28,604][00361] Num frames 9100... | |
| [2024-05-20 04:15:28,734][00361] Num frames 9200... | |
| [2024-05-20 04:15:28,883][00361] Num frames 9300... | |
| [2024-05-20 04:15:29,010][00361] Num frames 9400... | |
| [2024-05-20 04:15:29,150][00361] Num frames 9500... | |
| [2024-05-20 04:15:29,281][00361] Num frames 9600... | |
| [2024-05-20 04:15:29,426][00361] Num frames 9700... | |
| [2024-05-20 04:15:29,567][00361] Avg episode rewards: #0: 25.945, true rewards: #0: 10.834 | |
| [2024-05-20 04:15:29,569][00361] Avg episode reward: 25.945, avg true_objective: 10.834 | |
| [2024-05-20 04:15:29,640][00361] Num frames 9800... | |
| [2024-05-20 04:15:29,772][00361] Num frames 9900... | |
| [2024-05-20 04:15:29,909][00361] Num frames 10000... | |
| [2024-05-20 04:15:30,056][00361] Avg episode rewards: #0: 23.771, true rewards: #0: 10.071 | |
| [2024-05-20 04:15:30,059][00361] Avg episode reward: 23.771, avg true_objective: 10.071 | |
| [2024-05-20 04:16:33,904][00361] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-05-20 04:27:14,824][00361] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-05-20 04:27:14,830][00361] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-05-20 04:27:14,835][00361] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-05-20 04:27:14,841][00361] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-05-20 04:27:14,843][00361] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-05-20 04:27:14,845][00361] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-05-20 04:27:14,850][00361] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-05-20 04:27:14,851][00361] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-05-20 04:27:14,858][00361] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-05-20 04:27:14,860][00361] Adding new argument 'hf_repository'='pyupeu/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-05-20 04:27:14,861][00361] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-05-20 04:27:14,862][00361] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-05-20 04:27:14,863][00361] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-05-20 04:27:14,864][00361] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-05-20 04:27:14,865][00361] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-05-20 04:27:14,944][00361] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-05-20 04:27:14,951][00361] RunningMeanStd input shape: (1,) | |
| [2024-05-20 04:27:14,993][00361] ConvEncoder: input_channels=3 | |
| [2024-05-20 04:27:15,204][00361] Conv encoder output size: 512 | |
| [2024-05-20 04:27:15,214][00361] Policy head output size: 512 | |
| [2024-05-20 04:27:15,310][00361] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-05-20 04:27:16,208][00361] Num frames 100... | |
| [2024-05-20 04:27:16,398][00361] Num frames 200... | |
| [2024-05-20 04:27:16,581][00361] Num frames 300... | |
| [2024-05-20 04:27:16,777][00361] Num frames 400... | |
| [2024-05-20 04:27:16,937][00361] Num frames 500... | |
| [2024-05-20 04:27:17,079][00361] Num frames 600... | |
| [2024-05-20 04:27:17,211][00361] Num frames 700... | |
| [2024-05-20 04:27:17,344][00361] Num frames 800... | |
| [2024-05-20 04:27:17,486][00361] Num frames 900... | |
| [2024-05-20 04:27:17,622][00361] Num frames 1000... | |
| [2024-05-20 04:27:17,762][00361] Num frames 1100... | |
| [2024-05-20 04:27:17,902][00361] Num frames 1200... | |
| [2024-05-20 04:27:18,050][00361] Num frames 1300... | |
| [2024-05-20 04:27:18,195][00361] Num frames 1400... | |
| [2024-05-20 04:27:18,335][00361] Avg episode rewards: #0: 32.590, true rewards: #0: 14.590 | |
| [2024-05-20 04:27:18,337][00361] Avg episode reward: 32.590, avg true_objective: 14.590 | |
| [2024-05-20 04:27:18,398][00361] Num frames 1500... | |
| [2024-05-20 04:27:18,541][00361] Num frames 1600... | |
| [2024-05-20 04:27:18,683][00361] Num frames 1700... | |
| [2024-05-20 04:27:18,823][00361] Num frames 1800... | |
| [2024-05-20 04:27:18,970][00361] Num frames 1900... | |
| [2024-05-20 04:27:19,116][00361] Num frames 2000... | |
| [2024-05-20 04:27:19,261][00361] Num frames 2100... | |
| [2024-05-20 04:27:19,402][00361] Num frames 2200... | |
| [2024-05-20 04:27:19,544][00361] Num frames 2300... | |
| [2024-05-20 04:27:19,687][00361] Num frames 2400... | |
| [2024-05-20 04:27:19,823][00361] Num frames 2500... | |
| [2024-05-20 04:27:19,890][00361] Avg episode rewards: #0: 29.035, true rewards: #0: 12.535 | |
| [2024-05-20 04:27:19,892][00361] Avg episode reward: 29.035, avg true_objective: 12.535 | |
| [2024-05-20 04:27:20,024][00361] Num frames 2600... | |
| [2024-05-20 04:27:20,174][00361] Num frames 2700... | |
| [2024-05-20 04:27:20,310][00361] Num frames 2800... | |
| [2024-05-20 04:27:20,454][00361] Num frames 2900... | |
| [2024-05-20 04:27:20,590][00361] Num frames 3000... | |
| [2024-05-20 04:27:20,735][00361] Num frames 3100... | |
| [2024-05-20 04:27:20,873][00361] Num frames 3200... | |
| [2024-05-20 04:27:21,017][00361] Num frames 3300... | |
| [2024-05-20 04:27:21,171][00361] Num frames 3400... | |
| [2024-05-20 04:27:21,308][00361] Num frames 3500... | |
| [2024-05-20 04:27:21,451][00361] Num frames 3600... | |
| [2024-05-20 04:27:21,594][00361] Num frames 3700... | |
| [2024-05-20 04:27:21,736][00361] Num frames 3800... | |
| [2024-05-20 04:27:21,874][00361] Num frames 3900... | |
| [2024-05-20 04:27:22,009][00361] Num frames 4000... | |
| [2024-05-20 04:27:22,155][00361] Num frames 4100... | |
| [2024-05-20 04:27:22,223][00361] Avg episode rewards: #0: 34.690, true rewards: #0: 13.690 | |
| [2024-05-20 04:27:22,226][00361] Avg episode reward: 34.690, avg true_objective: 13.690 | |
| [2024-05-20 04:27:22,357][00361] Num frames 4200... | |
| [2024-05-20 04:27:22,497][00361] Num frames 4300... | |
| [2024-05-20 04:27:22,639][00361] Num frames 4400... | |
| [2024-05-20 04:27:22,721][00361] Avg episode rewards: #0: 27.297, true rewards: #0: 11.047 | |
| [2024-05-20 04:27:22,723][00361] Avg episode reward: 27.297, avg true_objective: 11.047 | |
| [2024-05-20 04:27:22,844][00361] Num frames 4500... | |
| [2024-05-20 04:27:22,981][00361] Num frames 4600... | |
| [2024-05-20 04:27:23,121][00361] Num frames 4700... | |
| [2024-05-20 04:27:23,253][00361] Num frames 4800... | |
| [2024-05-20 04:27:23,389][00361] Num frames 4900... | |
| [2024-05-20 04:27:23,516][00361] Num frames 5000... | |
| [2024-05-20 04:27:23,609][00361] Avg episode rewards: #0: 23.654, true rewards: #0: 10.054 | |
| [2024-05-20 04:27:23,611][00361] Avg episode reward: 23.654, avg true_objective: 10.054 | |
| [2024-05-20 04:27:23,709][00361] Num frames 5100... | |
| [2024-05-20 04:27:23,845][00361] Num frames 5200... | |
| [2024-05-20 04:27:23,972][00361] Num frames 5300... | |
| [2024-05-20 04:27:24,101][00361] Num frames 5400... | |
| [2024-05-20 04:27:24,241][00361] Num frames 5500... | |
| [2024-05-20 04:27:24,373][00361] Num frames 5600... | |
| [2024-05-20 04:27:24,505][00361] Num frames 5700... | |
| [2024-05-20 04:27:24,635][00361] Num frames 5800... | |
| [2024-05-20 04:27:24,764][00361] Num frames 5900... | |
| [2024-05-20 04:27:24,899][00361] Num frames 6000... | |
| [2024-05-20 04:27:25,035][00361] Num frames 6100... | |
| [2024-05-20 04:27:25,157][00361] Avg episode rewards: #0: 24.078, true rewards: #0: 10.245 | |
| [2024-05-20 04:27:25,159][00361] Avg episode reward: 24.078, avg true_objective: 10.245 | |
| [2024-05-20 04:27:25,237][00361] Num frames 6200... | |
| [2024-05-20 04:27:25,376][00361] Num frames 6300... | |
| [2024-05-20 04:27:25,512][00361] Num frames 6400... | |
| [2024-05-20 04:27:25,638][00361] Num frames 6500... | |
| [2024-05-20 04:27:25,769][00361] Avg episode rewards: #0: 21.361, true rewards: #0: 9.361 | |
| [2024-05-20 04:27:25,770][00361] Avg episode reward: 21.361, avg true_objective: 9.361 | |
| [2024-05-20 04:27:25,835][00361] Num frames 6600... | |
| [2024-05-20 04:27:25,966][00361] Num frames 6700... | |
| [2024-05-20 04:27:26,093][00361] Num frames 6800... | |
| [2024-05-20 04:27:26,233][00361] Num frames 6900... | |
| [2024-05-20 04:27:26,362][00361] Num frames 7000... | |
| [2024-05-20 04:27:26,488][00361] Num frames 7100... | |
| [2024-05-20 04:27:26,615][00361] Num frames 7200... | |
| [2024-05-20 04:27:26,750][00361] Num frames 7300... | |
| [2024-05-20 04:27:26,942][00361] Avg episode rewards: #0: 20.731, true rewards: #0: 9.231 | |
| [2024-05-20 04:27:26,945][00361] Avg episode reward: 20.731, avg true_objective: 9.231 | |
| [2024-05-20 04:27:26,985][00361] Num frames 7400... | |
| [2024-05-20 04:27:27,184][00361] Num frames 7500... | |
| [2024-05-20 04:27:27,383][00361] Num frames 7600... | |
| [2024-05-20 04:27:27,573][00361] Num frames 7700... | |
| [2024-05-20 04:27:27,759][00361] Num frames 7800... | |
| [2024-05-20 04:27:27,957][00361] Num frames 7900... | |
| [2024-05-20 04:27:28,148][00361] Num frames 8000... | |
| [2024-05-20 04:27:28,362][00361] Num frames 8100... | |
| [2024-05-20 04:27:28,561][00361] Num frames 8200... | |
| [2024-05-20 04:27:28,750][00361] Num frames 8300... | |
| [2024-05-20 04:27:28,952][00361] Num frames 8400... | |
| [2024-05-20 04:27:29,152][00361] Num frames 8500... | |
| [2024-05-20 04:27:29,362][00361] Num frames 8600... | |
| [2024-05-20 04:27:29,563][00361] Num frames 8700... | |
| [2024-05-20 04:27:29,704][00361] Num frames 8800... | |
| [2024-05-20 04:27:29,835][00361] Num frames 8900... | |
| [2024-05-20 04:27:29,971][00361] Num frames 9000... | |
| [2024-05-20 04:27:30,118][00361] Num frames 9100... | |
| [2024-05-20 04:27:30,254][00361] Num frames 9200... | |
| [2024-05-20 04:27:30,395][00361] Num frames 9300... | |
| [2024-05-20 04:27:30,572][00361] Avg episode rewards: #0: 24.660, true rewards: #0: 10.438 | |
| [2024-05-20 04:27:30,573][00361] Avg episode reward: 24.660, avg true_objective: 10.438 | |
| [2024-05-20 04:27:30,586][00361] Num frames 9400... | |
| [2024-05-20 04:27:30,720][00361] Num frames 9500... | |
| [2024-05-20 04:27:30,855][00361] Num frames 9600... | |
| [2024-05-20 04:27:31,000][00361] Num frames 9700... | |
| [2024-05-20 04:27:31,156][00361] Num frames 9800... | |
| [2024-05-20 04:27:31,299][00361] Num frames 9900... | |
| [2024-05-20 04:27:31,436][00361] Num frames 10000... | |
| [2024-05-20 04:27:31,540][00361] Avg episode rewards: #0: 23.434, true rewards: #0: 10.034 | |
| [2024-05-20 04:27:31,541][00361] Avg episode reward: 23.434, avg true_objective: 10.034 | |
| [2024-05-20 04:28:32,156][00361] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |