| [2023-02-23 12:54:19,706][00119] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-23 12:54:19,709][00119] Rollout worker 0 uses device cpu | |
| [2023-02-23 12:54:19,711][00119] Rollout worker 1 uses device cpu | |
| [2023-02-23 12:54:19,712][00119] Rollout worker 2 uses device cpu | |
| [2023-02-23 12:54:19,713][00119] Rollout worker 3 uses device cpu | |
| [2023-02-23 12:54:19,715][00119] Rollout worker 4 uses device cpu | |
| [2023-02-23 12:54:19,717][00119] Rollout worker 5 uses device cpu | |
| [2023-02-23 12:54:19,718][00119] Rollout worker 6 uses device cpu | |
| [2023-02-23 12:54:19,719][00119] Rollout worker 7 uses device cpu | |
| [2023-02-23 12:54:19,930][00119] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 12:54:19,933][00119] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-23 12:54:19,966][00119] Starting all processes... | |
| [2023-02-23 12:54:19,968][00119] Starting process learner_proc0 | |
| [2023-02-23 12:54:20,021][00119] Starting all processes... | |
| [2023-02-23 12:54:20,034][00119] Starting process inference_proc0-0 | |
| [2023-02-23 12:54:20,035][00119] Starting process rollout_proc0 | |
| [2023-02-23 12:54:20,037][00119] Starting process rollout_proc1 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc2 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc3 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc4 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc5 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc6 | |
| [2023-02-23 12:54:20,038][00119] Starting process rollout_proc7 | |
| [2023-02-23 12:54:31,455][12887] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 12:54:31,463][12887] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-23 12:54:31,613][12910] Worker 4 uses CPU cores [0] | |
| [2023-02-23 12:54:31,810][12912] Worker 6 uses CPU cores [0] | |
| [2023-02-23 12:54:32,151][12907] Worker 1 uses CPU cores [1] | |
| [2023-02-23 12:54:32,202][12908] Worker 2 uses CPU cores [0] | |
| [2023-02-23 12:54:32,245][12906] Worker 0 uses CPU cores [0] | |
| [2023-02-23 12:54:32,265][12909] Worker 3 uses CPU cores [1] | |
| [2023-02-23 12:54:32,281][12913] Worker 7 uses CPU cores [1] | |
| [2023-02-23 12:54:32,309][12911] Worker 5 uses CPU cores [1] | |
| [2023-02-23 12:54:32,322][12905] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 12:54:32,323][12905] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-23 12:54:32,332][12887] Num visible devices: 1 | |
| [2023-02-23 12:54:32,334][12887] Starting seed is not provided | |
| [2023-02-23 12:54:32,334][12887] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 12:54:32,334][12887] Initializing actor-critic model on device cuda:0 | |
| [2023-02-23 12:54:32,334][12887] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 12:54:32,336][12887] RunningMeanStd input shape: (1,) | |
| [2023-02-23 12:54:32,337][12905] Num visible devices: 1 | |
| [2023-02-23 12:54:32,352][12887] ConvEncoder: input_channels=3 | |
| [2023-02-23 12:54:32,645][12887] Conv encoder output size: 512 | |
| [2023-02-23 12:54:32,645][12887] Policy head output size: 512 | |
| [2023-02-23 12:54:32,701][12887] Created Actor Critic model with architecture: | |
| [2023-02-23 12:54:32,701][12887] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2023-02-23 12:54:39,921][00119] Heartbeat connected on Batcher_0 | |
| [2023-02-23 12:54:39,931][00119] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-23 12:54:39,940][00119] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-23 12:54:39,946][00119] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-23 12:54:39,949][00119] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-23 12:54:39,953][00119] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-23 12:54:39,956][00119] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-23 12:54:39,959][00119] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-23 12:54:39,963][00119] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-23 12:54:39,967][00119] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-23 12:54:41,319][12887] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-23 12:54:41,320][12887] No checkpoints found | |
| [2023-02-23 12:54:41,320][12887] Did not load from checkpoint, starting from scratch! | |
| [2023-02-23 12:54:41,320][12887] Initialized policy 0 weights for model version 0 | |
| [2023-02-23 12:54:41,324][12887] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 12:54:41,333][12887] LearnerWorker_p0 finished initialization! | |
| [2023-02-23 12:54:41,333][00119] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-23 12:54:41,537][12905] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 12:54:41,538][12905] RunningMeanStd input shape: (1,) | |
| [2023-02-23 12:54:41,551][12905] ConvEncoder: input_channels=3 | |
| [2023-02-23 12:54:41,654][12905] Conv encoder output size: 512 | |
| [2023-02-23 12:54:41,654][12905] Policy head output size: 512 | |
| [2023-02-23 12:54:43,881][00119] Inference worker 0-0 is ready! | |
| [2023-02-23 12:54:43,882][00119] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-23 12:54:44,004][12909] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,039][12911] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,033][12907] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,039][12908] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,044][12913] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,053][12910] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,061][12912] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,064][12906] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 12:54:44,924][12907] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:44,926][12909] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:44,926][12912] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:44,923][12908] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:45,302][12906] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:45,408][00119] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 12:54:45,656][12906] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:45,895][12913] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:45,951][12907] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:45,959][12909] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:46,400][12906] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:46,700][12913] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:46,951][12908] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:46,967][12909] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:47,124][12912] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:47,707][12907] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:47,748][12906] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:47,843][12911] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:48,226][12911] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:48,669][12909] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:48,704][12908] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:49,028][12912] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:49,137][12913] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:50,096][12907] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:50,279][12911] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:50,369][12913] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:50,410][00119] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 12:54:50,512][12910] Decorrelating experience for 0 frames... | |
| [2023-02-23 12:54:50,646][12908] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:50,868][12911] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:51,866][12910] Decorrelating experience for 32 frames... | |
| [2023-02-23 12:54:52,019][12912] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:52,518][12910] Decorrelating experience for 64 frames... | |
| [2023-02-23 12:54:53,102][12910] Decorrelating experience for 96 frames... | |
| [2023-02-23 12:54:55,408][00119] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 4.4. Samples: 44. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 12:54:55,411][00119] Avg episode reward: [(0, '1.200')] | |
| [2023-02-23 12:54:57,996][12887] Signal inference workers to stop experience collection... | |
| [2023-02-23 12:54:58,018][12905] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-23 12:55:00,408][00119] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 155.1. Samples: 2326. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 12:55:00,409][00119] Avg episode reward: [(0, '1.963')] | |
| [2023-02-23 12:55:00,459][12887] Signal inference workers to resume experience collection... | |
| [2023-02-23 12:55:00,461][12905] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-23 12:55:05,408][00119] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 319.6. Samples: 6392. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) | |
| [2023-02-23 12:55:05,413][00119] Avg episode reward: [(0, '3.452')] | |
| [2023-02-23 12:55:08,578][12905] Updated weights for policy 0, policy_version 10 (0.0011) | |
| [2023-02-23 12:55:10,412][00119] Fps is (10 sec: 4503.9, 60 sec: 1802.0, 300 sec: 1802.0). Total num frames: 45056. Throughput: 0: 388.8. Samples: 9722. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 12:55:10,414][00119] Avg episode reward: [(0, '4.128')] | |
| [2023-02-23 12:55:15,408][00119] Fps is (10 sec: 3276.8, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 482.5. Samples: 14476. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-23 12:55:15,415][00119] Avg episode reward: [(0, '4.378')] | |
| [2023-02-23 12:55:20,408][00119] Fps is (10 sec: 2868.3, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 73728. Throughput: 0: 543.5. Samples: 19024. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 12:55:20,410][00119] Avg episode reward: [(0, '4.510')] | |
| [2023-02-23 12:55:21,486][12905] Updated weights for policy 0, policy_version 20 (0.0023) | |
| [2023-02-23 12:55:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 560.7. Samples: 22430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:55:25,415][00119] Avg episode reward: [(0, '4.438')] | |
| [2023-02-23 12:55:30,408][00119] Fps is (10 sec: 4505.5, 60 sec: 2639.6, 300 sec: 2639.6). Total num frames: 118784. Throughput: 0: 649.1. Samples: 29210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:55:30,415][00119] Avg episode reward: [(0, '4.497')] | |
| [2023-02-23 12:55:30,420][12887] Saving new best policy, reward=4.497! | |
| [2023-02-23 12:55:31,717][12905] Updated weights for policy 0, policy_version 30 (0.0016) | |
| [2023-02-23 12:55:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 741.5. Samples: 33368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:55:35,411][00119] Avg episode reward: [(0, '4.638')] | |
| [2023-02-23 12:55:35,427][12887] Saving new best policy, reward=4.638! | |
| [2023-02-23 12:55:40,408][00119] Fps is (10 sec: 2867.2, 60 sec: 2681.0, 300 sec: 2681.0). Total num frames: 147456. Throughput: 0: 785.2. Samples: 35380. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 12:55:40,411][00119] Avg episode reward: [(0, '4.660')] | |
| [2023-02-23 12:55:40,413][12887] Saving new best policy, reward=4.660! | |
| [2023-02-23 12:55:43,650][12905] Updated weights for policy 0, policy_version 40 (0.0015) | |
| [2023-02-23 12:55:45,408][00119] Fps is (10 sec: 3686.4, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 872.7. Samples: 41598. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 12:55:45,410][00119] Avg episode reward: [(0, '4.442')] | |
| [2023-02-23 12:55:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3140.4, 300 sec: 2898.7). Total num frames: 188416. Throughput: 0: 921.1. Samples: 47842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:55:50,411][00119] Avg episode reward: [(0, '4.424')] | |
| [2023-02-23 12:55:55,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2867.2). Total num frames: 200704. Throughput: 0: 893.8. Samples: 49938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:55:55,411][00119] Avg episode reward: [(0, '4.475')] | |
| [2023-02-23 12:55:55,515][12905] Updated weights for policy 0, policy_version 50 (0.0020) | |
| [2023-02-23 12:56:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 2949.1). Total num frames: 221184. Throughput: 0: 884.1. Samples: 54262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:56:00,413][00119] Avg episode reward: [(0, '4.609')] | |
| [2023-02-23 12:56:05,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3020.8). Total num frames: 241664. Throughput: 0: 933.6. Samples: 61038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:56:05,415][00119] Avg episode reward: [(0, '4.565')] | |
| [2023-02-23 12:56:05,896][12905] Updated weights for policy 0, policy_version 60 (0.0019) | |
| [2023-02-23 12:56:10,411][00119] Fps is (10 sec: 4094.8, 60 sec: 3618.2, 300 sec: 3083.9). Total num frames: 262144. Throughput: 0: 930.7. Samples: 64316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:56:10,416][00119] Avg episode reward: [(0, '4.551')] | |
| [2023-02-23 12:56:15,410][00119] Fps is (10 sec: 3276.2, 60 sec: 3618.0, 300 sec: 3049.2). Total num frames: 274432. Throughput: 0: 882.7. Samples: 68934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:56:15,413][00119] Avg episode reward: [(0, '4.525')] | |
| [2023-02-23 12:56:15,424][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth... | |
| [2023-02-23 12:56:18,776][12905] Updated weights for policy 0, policy_version 70 (0.0020) | |
| [2023-02-23 12:56:20,408][00119] Fps is (10 sec: 2868.0, 60 sec: 3618.1, 300 sec: 3061.2). Total num frames: 290816. Throughput: 0: 889.4. Samples: 73392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:56:20,411][00119] Avg episode reward: [(0, '4.501')] | |
| [2023-02-23 12:56:25,408][00119] Fps is (10 sec: 4096.7, 60 sec: 3618.1, 300 sec: 3153.9). Total num frames: 315392. Throughput: 0: 918.8. Samples: 76724. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:56:25,410][00119] Avg episode reward: [(0, '4.467')] | |
| [2023-02-23 12:56:28,114][12905] Updated weights for policy 0, policy_version 80 (0.0012) | |
| [2023-02-23 12:56:30,413][00119] Fps is (10 sec: 4094.0, 60 sec: 3549.6, 300 sec: 3159.6). Total num frames: 331776. Throughput: 0: 930.3. Samples: 83468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:56:30,416][00119] Avg episode reward: [(0, '4.428')] | |
| [2023-02-23 12:56:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3165.1). Total num frames: 348160. Throughput: 0: 886.2. Samples: 87722. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:56:35,415][00119] Avg episode reward: [(0, '4.285')] | |
| [2023-02-23 12:56:40,408][00119] Fps is (10 sec: 3278.4, 60 sec: 3618.1, 300 sec: 3169.9). Total num frames: 364544. Throughput: 0: 888.2. Samples: 89908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:56:40,410][00119] Avg episode reward: [(0, '4.208')] | |
| [2023-02-23 12:56:40,844][12905] Updated weights for policy 0, policy_version 90 (0.0033) | |
| [2023-02-23 12:56:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3242.7). Total num frames: 389120. Throughput: 0: 932.8. Samples: 96240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 12:56:45,411][00119] Avg episode reward: [(0, '4.435')] | |
| [2023-02-23 12:56:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 921.5. Samples: 102504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:56:50,412][00119] Avg episode reward: [(0, '4.651')] | |
| [2023-02-23 12:56:50,726][12905] Updated weights for policy 0, policy_version 100 (0.0013) | |
| [2023-02-23 12:56:55,409][00119] Fps is (10 sec: 3276.5, 60 sec: 3686.3, 300 sec: 3245.3). Total num frames: 421888. Throughput: 0: 896.6. Samples: 104660. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:56:55,416][00119] Avg episode reward: [(0, '4.499')] | |
| [2023-02-23 12:57:00,408][00119] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3246.5). Total num frames: 438272. Throughput: 0: 887.7. Samples: 108878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 12:57:00,410][00119] Avg episode reward: [(0, '4.414')] | |
| [2023-02-23 12:57:02,804][12905] Updated weights for policy 0, policy_version 110 (0.0011) | |
| [2023-02-23 12:57:05,408][00119] Fps is (10 sec: 3686.7, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 458752. Throughput: 0: 936.6. Samples: 115538. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:57:05,413][00119] Avg episode reward: [(0, '4.483')] | |
| [2023-02-23 12:57:10,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3618.3, 300 sec: 3305.0). Total num frames: 479232. Throughput: 0: 936.9. Samples: 118886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:57:10,416][00119] Avg episode reward: [(0, '4.565')] | |
| [2023-02-23 12:57:13,830][12905] Updated weights for policy 0, policy_version 120 (0.0017) | |
| [2023-02-23 12:57:15,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3304.1). Total num frames: 495616. Throughput: 0: 890.3. Samples: 123526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 12:57:15,414][00119] Avg episode reward: [(0, '4.604')] | |
| [2023-02-23 12:57:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 899.6. Samples: 128206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:57:20,414][00119] Avg episode reward: [(0, '4.682')] | |
| [2023-02-23 12:57:20,415][12887] Saving new best policy, reward=4.682! | |
| [2023-02-23 12:57:25,036][12905] Updated weights for policy 0, policy_version 130 (0.0013) | |
| [2023-02-23 12:57:25,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3328.0). Total num frames: 532480. Throughput: 0: 921.9. Samples: 131392. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:57:25,411][00119] Avg episode reward: [(0, '4.708')] | |
| [2023-02-23 12:57:25,420][12887] Saving new best policy, reward=4.708! | |
| [2023-02-23 12:57:30,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3351.3). Total num frames: 552960. Throughput: 0: 928.5. Samples: 138024. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:57:30,413][00119] Avg episode reward: [(0, '4.544')] | |
| [2023-02-23 12:57:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 884.7. Samples: 142314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:57:35,410][00119] Avg episode reward: [(0, '4.401')] | |
| [2023-02-23 12:57:37,065][12905] Updated weights for policy 0, policy_version 140 (0.0023) | |
| [2023-02-23 12:57:40,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 885.1. Samples: 144488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 12:57:40,410][00119] Avg episode reward: [(0, '4.387')] | |
| [2023-02-23 12:57:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3367.8). Total num frames: 606208. Throughput: 0: 933.1. Samples: 150866. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:57:45,411][00119] Avg episode reward: [(0, '4.389')] | |
| [2023-02-23 12:57:46,999][12905] Updated weights for policy 0, policy_version 150 (0.0035) | |
| [2023-02-23 12:57:50,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3387.5). Total num frames: 626688. Throughput: 0: 923.6. Samples: 157100. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:57:50,415][00119] Avg episode reward: [(0, '4.425')] | |
| [2023-02-23 12:57:55,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3363.0). Total num frames: 638976. Throughput: 0: 897.0. Samples: 159250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:57:55,413][00119] Avg episode reward: [(0, '4.367')] | |
| [2023-02-23 12:57:59,676][12905] Updated weights for policy 0, policy_version 160 (0.0014) | |
| [2023-02-23 12:58:00,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 889.5. Samples: 163554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 12:58:00,411][00119] Avg episode reward: [(0, '4.448')] | |
| [2023-02-23 12:58:05,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3399.7). Total num frames: 679936. Throughput: 0: 937.5. Samples: 170392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:58:05,415][00119] Avg episode reward: [(0, '4.409')] | |
| [2023-02-23 12:58:08,807][12905] Updated weights for policy 0, policy_version 170 (0.0016) | |
| [2023-02-23 12:58:10,415][00119] Fps is (10 sec: 4502.5, 60 sec: 3686.0, 300 sec: 3416.5). Total num frames: 700416. Throughput: 0: 940.7. Samples: 173732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:58:10,418][00119] Avg episode reward: [(0, '4.505')] | |
| [2023-02-23 12:58:15,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 896.1. Samples: 178350. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:58:15,413][00119] Avg episode reward: [(0, '4.556')] | |
| [2023-02-23 12:58:15,423][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth... | |
| [2023-02-23 12:58:20,408][00119] Fps is (10 sec: 2869.2, 60 sec: 3618.1, 300 sec: 3391.1). Total num frames: 729088. Throughput: 0: 902.1. Samples: 182910. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:58:20,415][00119] Avg episode reward: [(0, '4.613')] | |
| [2023-02-23 12:58:21,751][12905] Updated weights for policy 0, policy_version 180 (0.0019) | |
| [2023-02-23 12:58:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3425.7). Total num frames: 753664. Throughput: 0: 928.4. Samples: 186268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 12:58:25,410][00119] Avg episode reward: [(0, '4.685')] | |
| [2023-02-23 12:58:30,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3422.4). Total num frames: 770048. Throughput: 0: 935.2. Samples: 192950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:58:30,411][00119] Avg episode reward: [(0, '4.587')] | |
| [2023-02-23 12:58:32,168][12905] Updated weights for policy 0, policy_version 190 (0.0028) | |
| [2023-02-23 12:58:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3419.3). Total num frames: 786432. Throughput: 0: 890.6. Samples: 197178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:58:35,411][00119] Avg episode reward: [(0, '4.584')] | |
| [2023-02-23 12:58:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3416.2). Total num frames: 802816. Throughput: 0: 891.0. Samples: 199344. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:58:40,415][00119] Avg episode reward: [(0, '4.427')] | |
| [2023-02-23 12:58:43,572][12905] Updated weights for policy 0, policy_version 200 (0.0015) | |
| [2023-02-23 12:58:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3447.5). Total num frames: 827392. Throughput: 0: 941.6. Samples: 205928. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 12:58:45,415][00119] Avg episode reward: [(0, '4.440')] | |
| [2023-02-23 12:58:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 923.8. Samples: 211964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:58:50,411][00119] Avg episode reward: [(0, '4.338')] | |
| [2023-02-23 12:58:54,959][12905] Updated weights for policy 0, policy_version 210 (0.0013) | |
| [2023-02-23 12:58:55,409][00119] Fps is (10 sec: 3276.5, 60 sec: 3686.3, 300 sec: 3440.6). Total num frames: 860160. Throughput: 0: 896.7. Samples: 214076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:58:55,412][00119] Avg episode reward: [(0, '4.391')] | |
| [2023-02-23 12:59:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3437.4). Total num frames: 876544. Throughput: 0: 891.6. Samples: 218474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:59:00,411][00119] Avg episode reward: [(0, '4.600')] | |
| [2023-02-23 12:59:05,408][00119] Fps is (10 sec: 3686.7, 60 sec: 3618.1, 300 sec: 3450.1). Total num frames: 897024. Throughput: 0: 936.7. Samples: 225062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 12:59:05,415][00119] Avg episode reward: [(0, '4.649')] | |
| [2023-02-23 12:59:05,477][12905] Updated weights for policy 0, policy_version 220 (0.0030) | |
| [2023-02-23 12:59:10,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3550.3, 300 sec: 3446.8). Total num frames: 913408. Throughput: 0: 928.5. Samples: 228050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:59:10,416][00119] Avg episode reward: [(0, '4.587')] | |
| [2023-02-23 12:59:15,408][00119] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3443.7). Total num frames: 929792. Throughput: 0: 872.5. Samples: 232214. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:59:15,416][00119] Avg episode reward: [(0, '4.441')] | |
| [2023-02-23 12:59:18,758][12905] Updated weights for policy 0, policy_version 230 (0.0016) | |
| [2023-02-23 12:59:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3440.6). Total num frames: 946176. Throughput: 0: 889.7. Samples: 237216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 12:59:20,414][00119] Avg episode reward: [(0, '4.609')] | |
| [2023-02-23 12:59:25,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3467.0). Total num frames: 970752. Throughput: 0: 916.9. Samples: 240606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:59:25,410][00119] Avg episode reward: [(0, '4.661')] | |
| [2023-02-23 12:59:27,922][12905] Updated weights for policy 0, policy_version 240 (0.0018) | |
| [2023-02-23 12:59:30,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3463.6). Total num frames: 987136. Throughput: 0: 913.4. Samples: 247030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:59:30,413][00119] Avg episode reward: [(0, '4.727')] | |
| [2023-02-23 12:59:30,416][12887] Saving new best policy, reward=4.727! | |
| [2023-02-23 12:59:35,412][00119] Fps is (10 sec: 3275.6, 60 sec: 3617.9, 300 sec: 3460.4). Total num frames: 1003520. Throughput: 0: 872.5. Samples: 251230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:59:35,415][00119] Avg episode reward: [(0, '4.678')] | |
| [2023-02-23 12:59:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 872.5. Samples: 253336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 12:59:40,411][00119] Avg episode reward: [(0, '4.727')] | |
| [2023-02-23 12:59:40,656][12905] Updated weights for policy 0, policy_version 250 (0.0022) | |
| [2023-02-23 12:59:45,408][00119] Fps is (10 sec: 3687.7, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 1040384. Throughput: 0: 922.7. Samples: 259994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 12:59:45,414][00119] Avg episode reward: [(0, '4.703')] | |
| [2023-02-23 12:59:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1060864. Throughput: 0: 906.2. Samples: 265840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 12:59:50,412][00119] Avg episode reward: [(0, '4.722')] | |
| [2023-02-23 12:59:51,328][12905] Updated weights for policy 0, policy_version 260 (0.0021) | |
| [2023-02-23 12:59:55,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1073152. Throughput: 0: 886.6. Samples: 267946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 12:59:55,413][00119] Avg episode reward: [(0, '4.776')] | |
| [2023-02-23 12:59:55,427][12887] Saving new best policy, reward=4.776! | |
| [2023-02-23 13:00:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1093632. Throughput: 0: 899.5. Samples: 272692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:00:00,414][00119] Avg episode reward: [(0, '4.806')] | |
| [2023-02-23 13:00:00,420][12887] Saving new best policy, reward=4.806! | |
| [2023-02-23 13:00:02,946][12905] Updated weights for policy 0, policy_version 270 (0.0018) | |
| [2023-02-23 13:00:05,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1114112. Throughput: 0: 936.7. Samples: 279366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:05,410][00119] Avg episode reward: [(0, '4.875')] | |
| [2023-02-23 13:00:05,425][12887] Saving new best policy, reward=4.875! | |
| [2023-02-23 13:00:10,409][00119] Fps is (10 sec: 4095.7, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1134592. Throughput: 0: 932.1. Samples: 282552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:10,412][00119] Avg episode reward: [(0, '4.857')] | |
| [2023-02-23 13:00:14,548][12905] Updated weights for policy 0, policy_version 280 (0.0023) | |
| [2023-02-23 13:00:15,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1146880. Throughput: 0: 884.2. Samples: 286820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:15,417][00119] Avg episode reward: [(0, '4.860')] | |
| [2023-02-23 13:00:15,428][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth... | |
| [2023-02-23 13:00:15,550][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth | |
| [2023-02-23 13:00:20,408][00119] Fps is (10 sec: 3277.1, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1167360. Throughput: 0: 908.8. Samples: 292122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:20,411][00119] Avg episode reward: [(0, '5.016')] | |
| [2023-02-23 13:00:20,417][12887] Saving new best policy, reward=5.016! | |
| [2023-02-23 13:00:24,860][12905] Updated weights for policy 0, policy_version 290 (0.0017) | |
| [2023-02-23 13:00:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1187840. Throughput: 0: 933.3. Samples: 295334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:00:25,411][00119] Avg episode reward: [(0, '4.928')] | |
| [2023-02-23 13:00:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1204224. Throughput: 0: 920.2. Samples: 301402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:30,413][00119] Avg episode reward: [(0, '5.016')] | |
| [2023-02-23 13:00:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3637.8). Total num frames: 1220608. Throughput: 0: 884.4. Samples: 305636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:00:35,410][00119] Avg episode reward: [(0, '5.161')] | |
| [2023-02-23 13:00:35,428][12887] Saving new best policy, reward=5.161! | |
| [2023-02-23 13:00:37,808][12905] Updated weights for policy 0, policy_version 300 (0.0018) | |
| [2023-02-23 13:00:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1236992. Throughput: 0: 886.6. Samples: 307844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:40,418][00119] Avg episode reward: [(0, '5.440')] | |
| [2023-02-23 13:00:40,425][12887] Saving new best policy, reward=5.440! | |
| [2023-02-23 13:00:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1261568. Throughput: 0: 931.4. Samples: 314604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:45,414][00119] Avg episode reward: [(0, '5.678')] | |
| [2023-02-23 13:00:45,427][12887] Saving new best policy, reward=5.678! | |
| [2023-02-23 13:00:47,015][12905] Updated weights for policy 0, policy_version 310 (0.0012) | |
| [2023-02-23 13:00:50,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1277952. Throughput: 0: 904.8. Samples: 320084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:00:50,411][00119] Avg episode reward: [(0, '5.542')] | |
| [2023-02-23 13:00:55,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1290240. Throughput: 0: 880.1. Samples: 322156. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:00:55,416][00119] Avg episode reward: [(0, '5.460')] | |
| [2023-02-23 13:00:59,820][12905] Updated weights for policy 0, policy_version 320 (0.0029) | |
| [2023-02-23 13:01:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1310720. Throughput: 0: 895.0. Samples: 327096. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:01:00,410][00119] Avg episode reward: [(0, '5.365')] | |
| [2023-02-23 13:01:05,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1331200. Throughput: 0: 927.4. Samples: 333856. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:01:05,413][00119] Avg episode reward: [(0, '5.500')] | |
| [2023-02-23 13:01:09,964][12905] Updated weights for policy 0, policy_version 330 (0.0025) | |
| [2023-02-23 13:01:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 1351680. Throughput: 0: 925.9. Samples: 337000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:01:10,415][00119] Avg episode reward: [(0, '5.482')] | |
| [2023-02-23 13:01:15,409][00119] Fps is (10 sec: 3276.5, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1363968. Throughput: 0: 884.3. Samples: 341196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:01:15,413][00119] Avg episode reward: [(0, '5.719')] | |
| [2023-02-23 13:01:15,429][12887] Saving new best policy, reward=5.719! | |
| [2023-02-23 13:01:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1384448. Throughput: 0: 906.8. Samples: 346440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:01:20,410][00119] Avg episode reward: [(0, '5.663')] | |
| [2023-02-23 13:01:22,009][12905] Updated weights for policy 0, policy_version 340 (0.0028) | |
| [2023-02-23 13:01:25,408][00119] Fps is (10 sec: 4096.3, 60 sec: 3618.1, 300 sec: 3637.9). Total num frames: 1404928. Throughput: 0: 931.3. Samples: 349752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:01:25,411][00119] Avg episode reward: [(0, '6.134')] | |
| [2023-02-23 13:01:25,426][12887] Saving new best policy, reward=6.134! | |
| [2023-02-23 13:01:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1421312. Throughput: 0: 913.2. Samples: 355698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:01:30,417][00119] Avg episode reward: [(0, '6.454')] | |
| [2023-02-23 13:01:30,419][12887] Saving new best policy, reward=6.454! | |
| [2023-02-23 13:01:33,621][12905] Updated weights for policy 0, policy_version 350 (0.0014) | |
| [2023-02-23 13:01:35,408][00119] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1437696. Throughput: 0: 884.6. Samples: 359890. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:01:35,411][00119] Avg episode reward: [(0, '6.798')] | |
| [2023-02-23 13:01:35,421][12887] Saving new best policy, reward=6.798! | |
| [2023-02-23 13:01:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1454080. Throughput: 0: 892.8. Samples: 362332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:01:40,414][00119] Avg episode reward: [(0, '7.371')] | |
| [2023-02-23 13:01:40,494][12887] Saving new best policy, reward=7.371! | |
| [2023-02-23 13:01:43,990][12905] Updated weights for policy 0, policy_version 360 (0.0031) | |
| [2023-02-23 13:01:45,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1478656. Throughput: 0: 931.7. Samples: 369024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:01:45,416][00119] Avg episode reward: [(0, '7.857')] | |
| [2023-02-23 13:01:45,428][12887] Saving new best policy, reward=7.857! | |
| [2023-02-23 13:01:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1495040. Throughput: 0: 905.4. Samples: 374598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:01:50,412][00119] Avg episode reward: [(0, '8.040')] | |
| [2023-02-23 13:01:50,414][12887] Saving new best policy, reward=8.040! | |
| [2023-02-23 13:01:55,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1511424. Throughput: 0: 879.7. Samples: 376588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:01:55,415][00119] Avg episode reward: [(0, '7.936')] | |
| [2023-02-23 13:01:56,694][12905] Updated weights for policy 0, policy_version 370 (0.0025) | |
| [2023-02-23 13:02:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1527808. Throughput: 0: 900.0. Samples: 381694. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:02:00,415][00119] Avg episode reward: [(0, '8.227')] | |
| [2023-02-23 13:02:00,419][12887] Saving new best policy, reward=8.227! | |
| [2023-02-23 13:02:05,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1552384. Throughput: 0: 933.6. Samples: 388450. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:02:05,416][00119] Avg episode reward: [(0, '8.564')] | |
| [2023-02-23 13:02:05,429][12887] Saving new best policy, reward=8.564! | |
| [2023-02-23 13:02:06,122][12905] Updated weights for policy 0, policy_version 380 (0.0020) | |
| [2023-02-23 13:02:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1568768. Throughput: 0: 924.9. Samples: 391372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:02:10,412][00119] Avg episode reward: [(0, '8.463')] | |
| [2023-02-23 13:02:15,411][00119] Fps is (10 sec: 2866.4, 60 sec: 3618.0, 300 sec: 3623.9). Total num frames: 1581056. Throughput: 0: 885.8. Samples: 395560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:02:15,414][00119] Avg episode reward: [(0, '8.611')] | |
| [2023-02-23 13:02:15,433][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth... | |
| [2023-02-23 13:02:15,549][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth | |
| [2023-02-23 13:02:15,569][12887] Saving new best policy, reward=8.611! | |
| [2023-02-23 13:02:18,977][12905] Updated weights for policy 0, policy_version 390 (0.0015) | |
| [2023-02-23 13:02:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1601536. Throughput: 0: 911.3. Samples: 400898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:02:20,413][00119] Avg episode reward: [(0, '8.482')] | |
| [2023-02-23 13:02:25,408][00119] Fps is (10 sec: 4097.1, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1622016. Throughput: 0: 928.8. Samples: 404130. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 13:02:25,411][00119] Avg episode reward: [(0, '9.343')] | |
| [2023-02-23 13:02:25,425][12887] Saving new best policy, reward=9.343! | |
| [2023-02-23 13:02:29,114][12905] Updated weights for policy 0, policy_version 400 (0.0012) | |
| [2023-02-23 13:02:30,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1642496. Throughput: 0: 909.4. Samples: 409946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:02:30,414][00119] Avg episode reward: [(0, '9.226')] | |
| [2023-02-23 13:02:35,409][00119] Fps is (10 sec: 3276.6, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1654784. Throughput: 0: 880.3. Samples: 414210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:02:35,412][00119] Avg episode reward: [(0, '10.127')] | |
| [2023-02-23 13:02:35,426][12887] Saving new best policy, reward=10.127! | |
| [2023-02-23 13:02:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1675264. Throughput: 0: 889.9. Samples: 416632. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:02:40,411][00119] Avg episode reward: [(0, '10.785')] | |
| [2023-02-23 13:02:40,415][12887] Saving new best policy, reward=10.785! | |
| [2023-02-23 13:02:41,407][12905] Updated weights for policy 0, policy_version 410 (0.0018) | |
| [2023-02-23 13:02:45,408][00119] Fps is (10 sec: 4096.3, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 1695744. Throughput: 0: 923.9. Samples: 423270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:02:45,410][00119] Avg episode reward: [(0, '10.835')] | |
| [2023-02-23 13:02:45,423][12887] Saving new best policy, reward=10.835! | |
| [2023-02-23 13:02:50,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1712128. Throughput: 0: 895.0. Samples: 428724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:02:50,414][00119] Avg episode reward: [(0, '10.644')] | |
| [2023-02-23 13:02:52,613][12905] Updated weights for policy 0, policy_version 420 (0.0013) | |
| [2023-02-23 13:02:55,410][00119] Fps is (10 sec: 2866.6, 60 sec: 3549.8, 300 sec: 3623.9). Total num frames: 1724416. Throughput: 0: 876.4. Samples: 430810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:02:55,415][00119] Avg episode reward: [(0, '10.273')] | |
| [2023-02-23 13:03:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1744896. Throughput: 0: 898.1. Samples: 435972. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 13:03:00,416][00119] Avg episode reward: [(0, '10.632')] | |
| [2023-02-23 13:03:03,269][12905] Updated weights for policy 0, policy_version 430 (0.0014) | |
| [2023-02-23 13:03:05,408][00119] Fps is (10 sec: 4506.5, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1769472. Throughput: 0: 931.0. Samples: 442792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:03:05,411][00119] Avg episode reward: [(0, '11.161')] | |
| [2023-02-23 13:03:05,420][12887] Saving new best policy, reward=11.161! | |
| [2023-02-23 13:03:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1785856. Throughput: 0: 920.8. Samples: 445564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:03:10,412][00119] Avg episode reward: [(0, '11.410')] | |
| [2023-02-23 13:03:10,414][12887] Saving new best policy, reward=11.410! | |
| [2023-02-23 13:03:15,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.3, 300 sec: 3623.9). Total num frames: 1798144. Throughput: 0: 884.5. Samples: 449748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:03:15,417][00119] Avg episode reward: [(0, '11.954')] | |
| [2023-02-23 13:03:15,438][12887] Saving new best policy, reward=11.954! | |
| [2023-02-23 13:03:15,877][12905] Updated weights for policy 0, policy_version 440 (0.0018) | |
| [2023-02-23 13:03:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1818624. Throughput: 0: 912.1. Samples: 455256. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:03:20,411][00119] Avg episode reward: [(0, '12.449')] | |
| [2023-02-23 13:03:20,417][12887] Saving new best policy, reward=12.449! | |
| [2023-02-23 13:03:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1839104. Throughput: 0: 930.4. Samples: 458500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:03:25,411][00119] Avg episode reward: [(0, '12.563')] | |
| [2023-02-23 13:03:25,419][12887] Saving new best policy, reward=12.563! | |
| [2023-02-23 13:03:25,703][12905] Updated weights for policy 0, policy_version 450 (0.0023) | |
| [2023-02-23 13:03:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 1855488. Throughput: 0: 910.4. Samples: 464236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:03:30,417][00119] Avg episode reward: [(0, '13.862')] | |
| [2023-02-23 13:03:30,419][12887] Saving new best policy, reward=13.862! | |
| [2023-02-23 13:03:35,408][00119] Fps is (10 sec: 3276.7, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 1871872. Throughput: 0: 883.1. Samples: 468462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:03:35,413][00119] Avg episode reward: [(0, '14.626')] | |
| [2023-02-23 13:03:35,429][12887] Saving new best policy, reward=14.626! | |
| [2023-02-23 13:03:38,378][12905] Updated weights for policy 0, policy_version 460 (0.0036) | |
| [2023-02-23 13:03:40,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1892352. Throughput: 0: 894.0. Samples: 471036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:03:40,416][00119] Avg episode reward: [(0, '15.108')] | |
| [2023-02-23 13:03:40,419][12887] Saving new best policy, reward=15.108! | |
| [2023-02-23 13:03:45,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1912832. Throughput: 0: 926.8. Samples: 477680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:03:45,411][00119] Avg episode reward: [(0, '14.758')] | |
| [2023-02-23 13:03:47,973][12905] Updated weights for policy 0, policy_version 470 (0.0017) | |
| [2023-02-23 13:03:50,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1929216. Throughput: 0: 895.3. Samples: 483080. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:03:50,416][00119] Avg episode reward: [(0, '13.866')] | |
| [2023-02-23 13:03:55,417][00119] Fps is (10 sec: 3273.9, 60 sec: 3686.0, 300 sec: 3623.8). Total num frames: 1945600. Throughput: 0: 881.2. Samples: 485224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:03:55,426][00119] Avg episode reward: [(0, '13.827')] | |
| [2023-02-23 13:04:00,412][12905] Updated weights for policy 0, policy_version 480 (0.0011) | |
| [2023-02-23 13:04:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1961984. Throughput: 0: 903.4. Samples: 490400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:04:00,416][00119] Avg episode reward: [(0, '13.144')] | |
| [2023-02-23 13:04:05,408][00119] Fps is (10 sec: 4099.5, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1986560. Throughput: 0: 931.1. Samples: 497156. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:04:05,411][00119] Avg episode reward: [(0, '13.698')] | |
| [2023-02-23 13:04:10,411][00119] Fps is (10 sec: 4094.7, 60 sec: 3617.9, 300 sec: 3637.8). Total num frames: 2002944. Throughput: 0: 920.7. Samples: 499934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:04:10,415][00119] Avg episode reward: [(0, '14.744')] | |
| [2023-02-23 13:04:11,387][12905] Updated weights for policy 0, policy_version 490 (0.0028) | |
| [2023-02-23 13:04:15,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2015232. Throughput: 0: 887.3. Samples: 504166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:04:15,412][00119] Avg episode reward: [(0, '15.159')] | |
| [2023-02-23 13:04:15,423][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth... | |
| [2023-02-23 13:04:15,579][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth | |
| [2023-02-23 13:04:15,614][12887] Saving new best policy, reward=15.159! | |
| [2023-02-23 13:04:20,408][00119] Fps is (10 sec: 3277.7, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2035712. Throughput: 0: 917.8. Samples: 509764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:04:20,411][00119] Avg episode reward: [(0, '14.798')] | |
| [2023-02-23 13:04:22,211][12905] Updated weights for policy 0, policy_version 500 (0.0046) | |
| [2023-02-23 13:04:25,408][00119] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2060288. Throughput: 0: 936.7. Samples: 513188. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:04:25,413][00119] Avg episode reward: [(0, '15.472')] | |
| [2023-02-23 13:04:25,427][12887] Saving new best policy, reward=15.472! | |
| [2023-02-23 13:04:30,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2076672. Throughput: 0: 914.4. Samples: 518828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:04:30,413][00119] Avg episode reward: [(0, '15.730')] | |
| [2023-02-23 13:04:30,418][12887] Saving new best policy, reward=15.730! | |
| [2023-02-23 13:04:34,475][12905] Updated weights for policy 0, policy_version 510 (0.0016) | |
| [2023-02-23 13:04:35,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2088960. Throughput: 0: 888.4. Samples: 523058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:04:35,418][00119] Avg episode reward: [(0, '14.750')] | |
| [2023-02-23 13:04:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2109440. Throughput: 0: 902.0. Samples: 525804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:04:40,411][00119] Avg episode reward: [(0, '15.204')] | |
| [2023-02-23 13:04:44,305][12905] Updated weights for policy 0, policy_version 520 (0.0040) | |
| [2023-02-23 13:04:45,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2134016. Throughput: 0: 937.1. Samples: 532568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:04:45,411][00119] Avg episode reward: [(0, '17.207')] | |
| [2023-02-23 13:04:45,422][12887] Saving new best policy, reward=17.207! | |
| [2023-02-23 13:04:50,409][00119] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3651.7). Total num frames: 2150400. Throughput: 0: 903.3. Samples: 537806. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:04:50,418][00119] Avg episode reward: [(0, '16.815')] | |
| [2023-02-23 13:04:55,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.7, 300 sec: 3623.9). Total num frames: 2162688. Throughput: 0: 889.4. Samples: 539952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:04:55,413][00119] Avg episode reward: [(0, '17.550')] | |
| [2023-02-23 13:04:55,431][12887] Saving new best policy, reward=17.550! | |
| [2023-02-23 13:04:57,187][12905] Updated weights for policy 0, policy_version 530 (0.0012) | |
| [2023-02-23 13:05:00,408][00119] Fps is (10 sec: 3277.1, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2183168. Throughput: 0: 913.2. Samples: 545258. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:05:00,411][00119] Avg episode reward: [(0, '16.801')] | |
| [2023-02-23 13:05:05,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2207744. Throughput: 0: 937.3. Samples: 551940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:05:05,411][00119] Avg episode reward: [(0, '17.672')] | |
| [2023-02-23 13:05:05,421][12887] Saving new best policy, reward=17.672! | |
| [2023-02-23 13:05:06,378][12905] Updated weights for policy 0, policy_version 540 (0.0021) | |
| [2023-02-23 13:05:10,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3637.8). Total num frames: 2220032. Throughput: 0: 920.6. Samples: 554614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:05:10,410][00119] Avg episode reward: [(0, '17.143')] | |
| [2023-02-23 13:05:15,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2236416. Throughput: 0: 890.5. Samples: 558900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:05:15,412][00119] Avg episode reward: [(0, '17.450')] | |
| [2023-02-23 13:05:19,033][12905] Updated weights for policy 0, policy_version 550 (0.0023) | |
| [2023-02-23 13:05:20,410][00119] Fps is (10 sec: 3685.7, 60 sec: 3686.3, 300 sec: 3623.9). Total num frames: 2256896. Throughput: 0: 925.5. Samples: 564706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:05:20,413][00119] Avg episode reward: [(0, '16.596')] | |
| [2023-02-23 13:05:25,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2277376. Throughput: 0: 938.9. Samples: 568056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:05:25,416][00119] Avg episode reward: [(0, '16.856')] | |
| [2023-02-23 13:05:29,362][12905] Updated weights for policy 0, policy_version 560 (0.0036) | |
| [2023-02-23 13:05:30,408][00119] Fps is (10 sec: 3687.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2293760. Throughput: 0: 915.3. Samples: 573758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:05:30,412][00119] Avg episode reward: [(0, '17.449')] | |
| [2023-02-23 13:05:35,408][00119] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2310144. Throughput: 0: 894.6. Samples: 578060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:05:35,415][00119] Avg episode reward: [(0, '18.327')] | |
| [2023-02-23 13:05:35,434][12887] Saving new best policy, reward=18.327! | |
| [2023-02-23 13:05:40,408][00119] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2330624. Throughput: 0: 907.0. Samples: 580768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:05:40,414][00119] Avg episode reward: [(0, '18.121')] | |
| [2023-02-23 13:05:41,073][12905] Updated weights for policy 0, policy_version 570 (0.0018) | |
| [2023-02-23 13:05:45,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2351104. Throughput: 0: 938.3. Samples: 587480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:05:45,416][00119] Avg episode reward: [(0, '19.743')] | |
| [2023-02-23 13:05:45,428][12887] Saving new best policy, reward=19.743! | |
| [2023-02-23 13:05:50,411][00119] Fps is (10 sec: 3685.5, 60 sec: 3618.0, 300 sec: 3651.7). Total num frames: 2367488. Throughput: 0: 908.8. Samples: 592838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:05:50,413][00119] Avg episode reward: [(0, '19.882')] | |
| [2023-02-23 13:05:50,416][12887] Saving new best policy, reward=19.882! | |
| [2023-02-23 13:05:52,233][12905] Updated weights for policy 0, policy_version 580 (0.0020) | |
| [2023-02-23 13:05:55,408][00119] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2383872. Throughput: 0: 894.4. Samples: 594864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:05:55,415][00119] Avg episode reward: [(0, '18.220')] | |
| [2023-02-23 13:06:00,408][00119] Fps is (10 sec: 3687.3, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2404352. Throughput: 0: 917.0. Samples: 600164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:06:00,417][00119] Avg episode reward: [(0, '17.711')] | |
| [2023-02-23 13:06:02,999][12905] Updated weights for policy 0, policy_version 590 (0.0020) | |
| [2023-02-23 13:06:05,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2424832. Throughput: 0: 937.3. Samples: 606884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:05,416][00119] Avg episode reward: [(0, '18.796')] | |
| [2023-02-23 13:06:10,414][00119] Fps is (10 sec: 3684.4, 60 sec: 3686.1, 300 sec: 3651.6). Total num frames: 2441216. Throughput: 0: 925.1. Samples: 609690. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:06:10,418][00119] Avg episode reward: [(0, '18.444')] | |
| [2023-02-23 13:06:15,210][12905] Updated weights for policy 0, policy_version 600 (0.0032) | |
| [2023-02-23 13:06:15,408][00119] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2457600. Throughput: 0: 893.6. Samples: 613968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:15,419][00119] Avg episode reward: [(0, '18.335')] | |
| [2023-02-23 13:06:15,439][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000600_2457600.pth... | |
| [2023-02-23 13:06:15,586][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth | |
| [2023-02-23 13:06:20,408][00119] Fps is (10 sec: 3688.4, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 2478080. Throughput: 0: 924.0. Samples: 619642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:20,412][00119] Avg episode reward: [(0, '19.269')] | |
| [2023-02-23 13:06:24,781][12905] Updated weights for policy 0, policy_version 610 (0.0021) | |
| [2023-02-23 13:06:25,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2498560. Throughput: 0: 939.0. Samples: 623022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:25,415][00119] Avg episode reward: [(0, '19.862')] | |
| [2023-02-23 13:06:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2514944. Throughput: 0: 917.7. Samples: 628778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:30,416][00119] Avg episode reward: [(0, '21.777')] | |
| [2023-02-23 13:06:30,417][12887] Saving new best policy, reward=21.777! | |
| [2023-02-23 13:06:35,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2527232. Throughput: 0: 892.7. Samples: 633008. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:06:35,416][00119] Avg episode reward: [(0, '21.924')] | |
| [2023-02-23 13:06:35,436][12887] Saving new best policy, reward=21.924! | |
| [2023-02-23 13:06:37,792][12905] Updated weights for policy 0, policy_version 620 (0.0039) | |
| [2023-02-23 13:06:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2547712. Throughput: 0: 907.2. Samples: 635690. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:06:40,414][00119] Avg episode reward: [(0, '21.555')] | |
| [2023-02-23 13:06:45,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2572288. Throughput: 0: 937.6. Samples: 642356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:06:45,411][00119] Avg episode reward: [(0, '21.231')] | |
| [2023-02-23 13:06:47,243][12905] Updated weights for policy 0, policy_version 630 (0.0020) | |
| [2023-02-23 13:06:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.6, 300 sec: 3651.7). Total num frames: 2588672. Throughput: 0: 904.8. Samples: 647602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:06:50,415][00119] Avg episode reward: [(0, '21.119')] | |
| [2023-02-23 13:06:55,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2600960. Throughput: 0: 890.2. Samples: 649746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:06:55,410][00119] Avg episode reward: [(0, '20.031')] | |
| [2023-02-23 13:06:59,676][12905] Updated weights for policy 0, policy_version 640 (0.0025) | |
| [2023-02-23 13:07:00,414][00119] Fps is (10 sec: 3274.9, 60 sec: 3617.8, 300 sec: 3623.8). Total num frames: 2621440. Throughput: 0: 912.9. Samples: 655056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:07:00,417][00119] Avg episode reward: [(0, '20.004')] | |
| [2023-02-23 13:07:05,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2646016. Throughput: 0: 940.5. Samples: 661964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:07:05,411][00119] Avg episode reward: [(0, '20.269')] | |
| [2023-02-23 13:07:09,859][12905] Updated weights for policy 0, policy_version 650 (0.0014) | |
| [2023-02-23 13:07:10,415][00119] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3665.5). Total num frames: 2662400. Throughput: 0: 925.3. Samples: 664668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:07:10,418][00119] Avg episode reward: [(0, '21.233')] | |
| [2023-02-23 13:07:15,410][00119] Fps is (10 sec: 2866.5, 60 sec: 3618.0, 300 sec: 3637.8). Total num frames: 2674688. Throughput: 0: 891.3. Samples: 668890. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:07:15,413][00119] Avg episode reward: [(0, '20.624')] | |
| [2023-02-23 13:07:20,408][00119] Fps is (10 sec: 3279.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2695168. Throughput: 0: 925.1. Samples: 674636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:07:20,415][00119] Avg episode reward: [(0, '21.724')] | |
| [2023-02-23 13:07:21,425][12905] Updated weights for policy 0, policy_version 660 (0.0029) | |
| [2023-02-23 13:07:25,408][00119] Fps is (10 sec: 4506.7, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2719744. Throughput: 0: 936.8. Samples: 677848. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:07:25,417][00119] Avg episode reward: [(0, '20.944')] | |
| [2023-02-23 13:07:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2732032. Throughput: 0: 909.8. Samples: 683296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:07:30,413][00119] Avg episode reward: [(0, '21.896')] | |
| [2023-02-23 13:07:33,815][12905] Updated weights for policy 0, policy_version 670 (0.0017) | |
| [2023-02-23 13:07:35,408][00119] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2744320. Throughput: 0: 882.8. Samples: 687328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:07:35,414][00119] Avg episode reward: [(0, '23.817')] | |
| [2023-02-23 13:07:35,448][12887] Saving new best policy, reward=23.817! | |
| [2023-02-23 13:07:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2764800. Throughput: 0: 890.1. Samples: 689800. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:07:40,411][00119] Avg episode reward: [(0, '23.375')] | |
| [2023-02-23 13:07:44,200][12905] Updated weights for policy 0, policy_version 680 (0.0023) | |
| [2023-02-23 13:07:45,408][00119] Fps is (10 sec: 4505.7, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2789376. Throughput: 0: 922.8. Samples: 696576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:07:45,416][00119] Avg episode reward: [(0, '21.676')] | |
| [2023-02-23 13:07:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2805760. Throughput: 0: 887.2. Samples: 701888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:07:50,416][00119] Avg episode reward: [(0, '21.846')] | |
| [2023-02-23 13:07:55,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2818048. Throughput: 0: 873.9. Samples: 703986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:07:55,411][00119] Avg episode reward: [(0, '20.235')] | |
| [2023-02-23 13:07:57,094][12905] Updated weights for policy 0, policy_version 690 (0.0021) | |
| [2023-02-23 13:08:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.5, 300 sec: 3623.9). Total num frames: 2838528. Throughput: 0: 894.8. Samples: 709154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:08:00,411][00119] Avg episode reward: [(0, '18.847')] | |
| [2023-02-23 13:08:05,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2863104. Throughput: 0: 916.2. Samples: 715864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:08:05,419][00119] Avg episode reward: [(0, '18.196')] | |
| [2023-02-23 13:08:06,312][12905] Updated weights for policy 0, policy_version 700 (0.0034) | |
| [2023-02-23 13:08:10,410][00119] Fps is (10 sec: 3685.8, 60 sec: 3550.2, 300 sec: 3651.7). Total num frames: 2875392. Throughput: 0: 905.4. Samples: 718592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:08:10,415][00119] Avg episode reward: [(0, '19.983')] | |
| [2023-02-23 13:08:15,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.3, 300 sec: 3637.8). Total num frames: 2891776. Throughput: 0: 880.2. Samples: 722904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:08:15,417][00119] Avg episode reward: [(0, '19.520')] | |
| [2023-02-23 13:08:15,434][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000706_2891776.pth... | |
| [2023-02-23 13:08:15,618][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth | |
| [2023-02-23 13:08:19,194][12905] Updated weights for policy 0, policy_version 710 (0.0025) | |
| [2023-02-23 13:08:20,408][00119] Fps is (10 sec: 3687.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2912256. Throughput: 0: 914.8. Samples: 728496. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:08:20,411][00119] Avg episode reward: [(0, '19.682')] | |
| [2023-02-23 13:08:25,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2932736. Throughput: 0: 933.2. Samples: 731794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:08:25,410][00119] Avg episode reward: [(0, '20.823')] | |
| [2023-02-23 13:08:29,349][12905] Updated weights for policy 0, policy_version 720 (0.0022) | |
| [2023-02-23 13:08:30,412][00119] Fps is (10 sec: 3684.9, 60 sec: 3617.9, 300 sec: 3651.6). Total num frames: 2949120. Throughput: 0: 910.9. Samples: 737568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:08:30,415][00119] Avg episode reward: [(0, '21.031')] | |
| [2023-02-23 13:08:35,409][00119] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2965504. Throughput: 0: 888.7. Samples: 741878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:08:35,410][00119] Avg episode reward: [(0, '21.357')] | |
| [2023-02-23 13:08:40,408][00119] Fps is (10 sec: 3687.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2985984. Throughput: 0: 901.3. Samples: 744546. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:08:40,413][00119] Avg episode reward: [(0, '21.037')] | |
| [2023-02-23 13:08:41,088][12905] Updated weights for policy 0, policy_version 730 (0.0021) | |
| [2023-02-23 13:08:45,408][00119] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3006464. Throughput: 0: 935.6. Samples: 751258. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:08:45,411][00119] Avg episode reward: [(0, '21.309')] | |
| [2023-02-23 13:08:50,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.8). Total num frames: 3022848. Throughput: 0: 905.6. Samples: 756618. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:08:50,410][00119] Avg episode reward: [(0, '20.932')] | |
| [2023-02-23 13:08:52,324][12905] Updated weights for policy 0, policy_version 740 (0.0039) | |
| [2023-02-23 13:08:55,409][00119] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3039232. Throughput: 0: 891.0. Samples: 758686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:08:55,413][00119] Avg episode reward: [(0, '20.478')] | |
| [2023-02-23 13:09:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3055616. Throughput: 0: 907.6. Samples: 763748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:09:00,410][00119] Avg episode reward: [(0, '21.164')] | |
| [2023-02-23 13:09:03,343][12905] Updated weights for policy 0, policy_version 750 (0.0019) | |
| [2023-02-23 13:09:05,408][00119] Fps is (10 sec: 4096.3, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3080192. Throughput: 0: 934.2. Samples: 770536. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 13:09:05,416][00119] Avg episode reward: [(0, '21.485')] | |
| [2023-02-23 13:09:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3665.6). Total num frames: 3096576. Throughput: 0: 926.0. Samples: 773466. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 13:09:10,413][00119] Avg episode reward: [(0, '21.106')] | |
| [2023-02-23 13:09:15,410][00119] Fps is (10 sec: 2866.7, 60 sec: 3618.0, 300 sec: 3637.8). Total num frames: 3108864. Throughput: 0: 893.2. Samples: 777758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:09:15,412][00119] Avg episode reward: [(0, '21.948')] | |
| [2023-02-23 13:09:15,464][12905] Updated weights for policy 0, policy_version 760 (0.0024) | |
| [2023-02-23 13:09:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3129344. Throughput: 0: 916.3. Samples: 783112. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 13:09:20,414][00119] Avg episode reward: [(0, '22.794')] | |
| [2023-02-23 13:09:25,248][12905] Updated weights for policy 0, policy_version 770 (0.0048) | |
| [2023-02-23 13:09:25,408][00119] Fps is (10 sec: 4506.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3153920. Throughput: 0: 933.3. Samples: 786544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:09:25,413][00119] Avg episode reward: [(0, '22.596')] | |
| [2023-02-23 13:09:30,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.6, 300 sec: 3665.6). Total num frames: 3170304. Throughput: 0: 914.6. Samples: 792416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:09:30,415][00119] Avg episode reward: [(0, '22.367')] | |
| [2023-02-23 13:09:35,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 3182592. Throughput: 0: 888.8. Samples: 796614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:09:35,417][00119] Avg episode reward: [(0, '21.518')] | |
| [2023-02-23 13:09:38,060][12905] Updated weights for policy 0, policy_version 780 (0.0030) | |
| [2023-02-23 13:09:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3203072. Throughput: 0: 896.5. Samples: 799026. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:09:40,416][00119] Avg episode reward: [(0, '21.375')] | |
| [2023-02-23 13:09:45,408][00119] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3227648. Throughput: 0: 933.6. Samples: 805760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:09:45,416][00119] Avg episode reward: [(0, '20.335')] | |
| [2023-02-23 13:09:47,178][12905] Updated weights for policy 0, policy_version 790 (0.0025) | |
| [2023-02-23 13:09:50,410][00119] Fps is (10 sec: 4095.2, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 3244032. Throughput: 0: 909.7. Samples: 811476. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:09:50,413][00119] Avg episode reward: [(0, '19.573')] | |
| [2023-02-23 13:09:55,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 3256320. Throughput: 0: 891.6. Samples: 813586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:09:55,411][00119] Avg episode reward: [(0, '20.012')] | |
| [2023-02-23 13:10:00,070][12905] Updated weights for policy 0, policy_version 800 (0.0033) | |
| [2023-02-23 13:10:00,408][00119] Fps is (10 sec: 3277.4, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3276800. Throughput: 0: 904.8. Samples: 818474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:10:00,411][00119] Avg episode reward: [(0, '20.512')] | |
| [2023-02-23 13:10:05,408][00119] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3301376. Throughput: 0: 935.4. Samples: 825204. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:10:05,410][00119] Avg episode reward: [(0, '21.073')] | |
| [2023-02-23 13:10:10,252][12905] Updated weights for policy 0, policy_version 810 (0.0012) | |
| [2023-02-23 13:10:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3317760. Throughput: 0: 928.5. Samples: 828328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:10:10,415][00119] Avg episode reward: [(0, '22.542')] | |
| [2023-02-23 13:10:15,408][00119] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 3330048. Throughput: 0: 892.4. Samples: 832572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:10:15,411][00119] Avg episode reward: [(0, '22.378')] | |
| [2023-02-23 13:10:15,426][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000813_3330048.pth... | |
| [2023-02-23 13:10:15,625][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000600_2457600.pth | |
| [2023-02-23 13:10:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3350528. Throughput: 0: 916.5. Samples: 837858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:10:20,410][00119] Avg episode reward: [(0, '22.877')] | |
| [2023-02-23 13:10:22,170][12905] Updated weights for policy 0, policy_version 820 (0.0028) | |
| [2023-02-23 13:10:25,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3371008. Throughput: 0: 937.0. Samples: 841190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:10:25,411][00119] Avg episode reward: [(0, '21.704')] | |
| [2023-02-23 13:10:30,410][00119] Fps is (10 sec: 4095.3, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 3391488. Throughput: 0: 924.6. Samples: 847368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:10:30,414][00119] Avg episode reward: [(0, '21.717')] | |
| [2023-02-23 13:10:33,383][12905] Updated weights for policy 0, policy_version 830 (0.0027) | |
| [2023-02-23 13:10:35,408][00119] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3403776. Throughput: 0: 891.5. Samples: 851590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:10:35,412][00119] Avg episode reward: [(0, '22.259')] | |
| [2023-02-23 13:10:40,408][00119] Fps is (10 sec: 3277.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3424256. Throughput: 0: 896.2. Samples: 853916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:10:40,416][00119] Avg episode reward: [(0, '21.823')] | |
| [2023-02-23 13:10:44,051][12905] Updated weights for policy 0, policy_version 840 (0.0031) | |
| [2023-02-23 13:10:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3444736. Throughput: 0: 937.2. Samples: 860646. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:10:45,416][00119] Avg episode reward: [(0, '20.911')] | |
| [2023-02-23 13:10:50,408][00119] Fps is (10 sec: 4095.8, 60 sec: 3686.5, 300 sec: 3665.6). Total num frames: 3465216. Throughput: 0: 917.2. Samples: 866480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:10:50,418][00119] Avg episode reward: [(0, '22.025')] | |
| [2023-02-23 13:10:55,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3477504. Throughput: 0: 894.4. Samples: 868574. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:10:55,412][00119] Avg episode reward: [(0, '21.149')] | |
| [2023-02-23 13:10:56,122][12905] Updated weights for policy 0, policy_version 850 (0.0029) | |
| [2023-02-23 13:11:00,408][00119] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3497984. Throughput: 0: 906.4. Samples: 873360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:11:00,410][00119] Avg episode reward: [(0, '20.146')] | |
| [2023-02-23 13:11:05,408][00119] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3651.8). Total num frames: 3518464. Throughput: 0: 939.0. Samples: 880112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:05,416][00119] Avg episode reward: [(0, '19.302')] | |
| [2023-02-23 13:11:05,999][12905] Updated weights for policy 0, policy_version 860 (0.0019) | |
| [2023-02-23 13:11:10,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3534848. Throughput: 0: 936.1. Samples: 883314. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:10,416][00119] Avg episode reward: [(0, '20.842')] | |
| [2023-02-23 13:11:15,408][00119] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3551232. Throughput: 0: 893.4. Samples: 887570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:11:15,415][00119] Avg episode reward: [(0, '22.176')] | |
| [2023-02-23 13:11:18,792][12905] Updated weights for policy 0, policy_version 870 (0.0048) | |
| [2023-02-23 13:11:20,409][00119] Fps is (10 sec: 3276.5, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3567616. Throughput: 0: 912.8. Samples: 892668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:11:20,411][00119] Avg episode reward: [(0, '22.489')] | |
| [2023-02-23 13:11:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3592192. Throughput: 0: 936.2. Samples: 896044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:25,411][00119] Avg episode reward: [(0, '23.951')] | |
| [2023-02-23 13:11:25,420][12887] Saving new best policy, reward=23.951! | |
| [2023-02-23 13:11:27,997][12905] Updated weights for policy 0, policy_version 880 (0.0013) | |
| [2023-02-23 13:11:30,408][00119] Fps is (10 sec: 4096.4, 60 sec: 3618.2, 300 sec: 3665.6). Total num frames: 3608576. Throughput: 0: 926.5. Samples: 902340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:30,416][00119] Avg episode reward: [(0, '24.616')] | |
| [2023-02-23 13:11:30,418][12887] Saving new best policy, reward=24.616! | |
| [2023-02-23 13:11:35,410][00119] Fps is (10 sec: 3276.2, 60 sec: 3686.3, 300 sec: 3651.7). Total num frames: 3624960. Throughput: 0: 889.6. Samples: 906512. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:35,414][00119] Avg episode reward: [(0, '25.091')] | |
| [2023-02-23 13:11:35,427][12887] Saving new best policy, reward=25.091! | |
| [2023-02-23 13:11:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3641344. Throughput: 0: 889.3. Samples: 908592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 13:11:40,415][00119] Avg episode reward: [(0, '23.872')] | |
| [2023-02-23 13:11:40,905][12905] Updated weights for policy 0, policy_version 890 (0.0021) | |
| [2023-02-23 13:11:45,408][00119] Fps is (10 sec: 3687.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3661824. Throughput: 0: 932.1. Samples: 915306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:11:45,413][00119] Avg episode reward: [(0, '22.172')] | |
| [2023-02-23 13:11:50,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3665.6). Total num frames: 3682304. Throughput: 0: 912.0. Samples: 921152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:11:50,413][00119] Avg episode reward: [(0, '21.678')] | |
| [2023-02-23 13:11:51,368][12905] Updated weights for policy 0, policy_version 900 (0.0013) | |
| [2023-02-23 13:11:55,409][00119] Fps is (10 sec: 3276.3, 60 sec: 3618.0, 300 sec: 3637.9). Total num frames: 3694592. Throughput: 0: 887.6. Samples: 923258. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:11:55,412][00119] Avg episode reward: [(0, '21.554')] | |
| [2023-02-23 13:12:00,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3715072. Throughput: 0: 897.8. Samples: 927972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:12:00,412][00119] Avg episode reward: [(0, '22.440')] | |
| [2023-02-23 13:12:02,870][12905] Updated weights for policy 0, policy_version 910 (0.0012) | |
| [2023-02-23 13:12:05,408][00119] Fps is (10 sec: 4096.6, 60 sec: 3618.1, 300 sec: 3637.9). Total num frames: 3735552. Throughput: 0: 932.6. Samples: 934636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:05,416][00119] Avg episode reward: [(0, '23.014')] | |
| [2023-02-23 13:12:10,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3756032. Throughput: 0: 932.9. Samples: 938024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:12:10,411][00119] Avg episode reward: [(0, '23.637')] | |
| [2023-02-23 13:12:14,611][12905] Updated weights for policy 0, policy_version 920 (0.0014) | |
| [2023-02-23 13:12:15,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3768320. Throughput: 0: 886.7. Samples: 942242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 13:12:15,411][00119] Avg episode reward: [(0, '24.389')] | |
| [2023-02-23 13:12:15,429][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000920_3768320.pth... | |
| [2023-02-23 13:12:15,588][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000706_2891776.pth | |
| [2023-02-23 13:12:20,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3623.9). Total num frames: 3788800. Throughput: 0: 906.8. Samples: 947314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:20,416][00119] Avg episode reward: [(0, '24.593')] | |
| [2023-02-23 13:12:24,914][12905] Updated weights for policy 0, policy_version 930 (0.0015) | |
| [2023-02-23 13:12:25,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3809280. Throughput: 0: 934.2. Samples: 950630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:25,415][00119] Avg episode reward: [(0, '23.900')] | |
| [2023-02-23 13:12:30,408][00119] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 3825664. Throughput: 0: 924.3. Samples: 956900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:30,411][00119] Avg episode reward: [(0, '24.256')] | |
| [2023-02-23 13:12:35,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3651.7). Total num frames: 3842048. Throughput: 0: 888.6. Samples: 961138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:35,419][00119] Avg episode reward: [(0, '24.533')] | |
| [2023-02-23 13:12:37,812][12905] Updated weights for policy 0, policy_version 940 (0.0018) | |
| [2023-02-23 13:12:40,408][00119] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3858432. Throughput: 0: 889.1. Samples: 963264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:12:40,411][00119] Avg episode reward: [(0, '24.642')] | |
| [2023-02-23 13:12:45,408][00119] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3883008. Throughput: 0: 934.4. Samples: 970018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:12:45,410][00119] Avg episode reward: [(0, '23.598')] | |
| [2023-02-23 13:12:46,844][12905] Updated weights for policy 0, policy_version 950 (0.0020) | |
| [2023-02-23 13:12:50,408][00119] Fps is (10 sec: 4095.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 3899392. Throughput: 0: 913.7. Samples: 975754. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 13:12:50,411][00119] Avg episode reward: [(0, '23.332')] | |
| [2023-02-23 13:12:55,409][00119] Fps is (10 sec: 3276.3, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3915776. Throughput: 0: 885.9. Samples: 977890. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 13:12:55,416][00119] Avg episode reward: [(0, '23.555')] | |
| [2023-02-23 13:12:59,724][12905] Updated weights for policy 0, policy_version 960 (0.0020) | |
| [2023-02-23 13:13:00,408][00119] Fps is (10 sec: 3277.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3932160. Throughput: 0: 896.8. Samples: 982600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 13:13:00,415][00119] Avg episode reward: [(0, '23.645')] | |
| [2023-02-23 13:13:05,408][00119] Fps is (10 sec: 4096.6, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3956736. Throughput: 0: 935.7. Samples: 989420. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 13:13:05,410][00119] Avg episode reward: [(0, '22.939')] | |
| [2023-02-23 13:13:09,436][12905] Updated weights for policy 0, policy_version 970 (0.0012) | |
| [2023-02-23 13:13:10,413][00119] Fps is (10 sec: 4094.0, 60 sec: 3617.8, 300 sec: 3665.5). Total num frames: 3973120. Throughput: 0: 934.9. Samples: 992704. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:13:10,418][00119] Avg episode reward: [(0, '23.370')] | |
| [2023-02-23 13:13:15,409][00119] Fps is (10 sec: 2867.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3985408. Throughput: 0: 889.0. Samples: 996904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 13:13:15,411][00119] Avg episode reward: [(0, '23.871')] | |
| [2023-02-23 13:13:19,991][00119] Component Batcher_0 stopped! | |
| [2023-02-23 13:13:19,990][12887] Stopping Batcher_0... | |
| [2023-02-23 13:13:19,993][12887] Loop batcher_evt_loop terminating... | |
| [2023-02-23 13:13:19,995][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 13:13:20,043][12905] Weights refcount: 2 0 | |
| [2023-02-23 13:13:20,052][00119] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-23 13:13:20,054][12905] Stopping InferenceWorker_p0-w0... | |
| [2023-02-23 13:13:20,055][12905] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-23 13:13:20,062][00119] Component RolloutWorker_w0 stopped! | |
| [2023-02-23 13:13:20,067][12906] Stopping RolloutWorker_w0... | |
| [2023-02-23 13:13:20,071][00119] Component RolloutWorker_w2 stopped! | |
| [2023-02-23 13:13:20,075][00119] Component RolloutWorker_w1 stopped! | |
| [2023-02-23 13:13:20,080][12908] Stopping RolloutWorker_w2... | |
| [2023-02-23 13:13:20,080][12908] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-23 13:13:20,087][00119] Component RolloutWorker_w4 stopped! | |
| [2023-02-23 13:13:20,069][12906] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-23 13:13:20,091][12910] Stopping RolloutWorker_w4... | |
| [2023-02-23 13:13:20,072][12907] Stopping RolloutWorker_w1... | |
| [2023-02-23 13:13:20,095][00119] Component RolloutWorker_w6 stopped! | |
| [2023-02-23 13:13:20,099][12912] Stopping RolloutWorker_w6... | |
| [2023-02-23 13:13:20,103][12909] Stopping RolloutWorker_w3... | |
| [2023-02-23 13:13:20,103][00119] Component RolloutWorker_w3 stopped! | |
| [2023-02-23 13:13:20,095][12907] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-23 13:13:20,094][12910] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-23 13:13:20,104][12909] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-23 13:13:20,100][12912] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-23 13:13:20,119][12911] Stopping RolloutWorker_w5... | |
| [2023-02-23 13:13:20,117][00119] Component RolloutWorker_w7 stopped! | |
| [2023-02-23 13:13:20,117][12913] Stopping RolloutWorker_w7... | |
| [2023-02-23 13:13:20,122][00119] Component RolloutWorker_w5 stopped! | |
| [2023-02-23 13:13:20,121][12911] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-23 13:13:20,127][12913] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-23 13:13:20,168][12887] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000813_3330048.pth | |
| [2023-02-23 13:13:20,184][12887] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 13:13:20,330][12887] Stopping LearnerWorker_p0... | |
| [2023-02-23 13:13:20,330][00119] Component LearnerWorker_p0 stopped! | |
| [2023-02-23 13:13:20,338][00119] Waiting for process learner_proc0 to stop... | |
| [2023-02-23 13:13:20,338][12887] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-23 13:13:22,158][00119] Waiting for process inference_proc0-0 to join... | |
| [2023-02-23 13:13:22,692][00119] Waiting for process rollout_proc0 to join... | |
| [2023-02-23 13:13:22,694][00119] Waiting for process rollout_proc1 to join... | |
| [2023-02-23 13:13:22,983][00119] Waiting for process rollout_proc2 to join... | |
| [2023-02-23 13:13:22,985][00119] Waiting for process rollout_proc3 to join... | |
| [2023-02-23 13:13:22,991][00119] Waiting for process rollout_proc4 to join... | |
| [2023-02-23 13:13:22,992][00119] Waiting for process rollout_proc5 to join... | |
| [2023-02-23 13:13:22,993][00119] Waiting for process rollout_proc6 to join... | |
| [2023-02-23 13:13:22,994][00119] Waiting for process rollout_proc7 to join... | |
| [2023-02-23 13:13:23,006][00119] Batcher 0 profile tree view: | |
| batching: 25.5939, releasing_batches: 0.0295 | |
| [2023-02-23 13:13:23,007][00119] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0056 | |
| wait_policy_total: 550.6084 | |
| update_model: 7.9728 | |
| weight_update: 0.0029 | |
| one_step: 0.0042 | |
| handle_policy_step: 515.2166 | |
| deserialize: 15.3736, stack: 3.0075, obs_to_device_normalize: 114.8605, forward: 247.9493, send_messages: 25.9685 | |
| prepare_outputs: 82.0699 | |
| to_cpu: 50.1613 | |
| [2023-02-23 13:13:23,008][00119] Learner 0 profile tree view: | |
| misc: 0.0060, prepare_batch: 17.2110 | |
| train: 75.7436 | |
| epoch_init: 0.0083, minibatch_init: 0.0214, losses_postprocess: 0.6318, kl_divergence: 0.6072, after_optimizer: 32.8299 | |
| calculate_losses: 26.7460 | |
| losses_init: 0.0044, forward_head: 1.7412, bptt_initial: 17.5625, tail: 1.0872, advantages_returns: 0.2539, losses: 3.4907 | |
| bptt: 2.3195 | |
| bptt_forward_core: 2.2107 | |
| update: 14.2638 | |
| clip: 1.4364 | |
| [2023-02-23 13:13:23,010][00119] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.2694, enqueue_policy_requests: 154.9148, env_step: 832.5016, overhead: 21.8111, complete_rollouts: 6.7096 | |
| save_policy_outputs: 20.9565 | |
| split_output_tensors: 10.0709 | |
| [2023-02-23 13:13:23,011][00119] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3154, enqueue_policy_requests: 154.3716, env_step: 832.9945, overhead: 21.8360, complete_rollouts: 7.0315 | |
| save_policy_outputs: 19.9334 | |
| split_output_tensors: 9.6806 | |
| [2023-02-23 13:13:23,014][00119] Loop Runner_EvtLoop terminating... | |
| [2023-02-23 13:13:23,015][00119] Runner profile tree view: | |
| main_loop: 1143.0496 | |
| [2023-02-23 13:13:23,017][00119] Collected {0: 4005888}, FPS: 3504.6 | |
| [2023-02-23 13:44:31,602][00119] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 13:44:31,606][00119] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 13:44:31,608][00119] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 13:44:31,612][00119] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 13:44:31,615][00119] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 13:44:31,617][00119] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 13:44:31,619][00119] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 13:44:31,624][00119] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 13:44:31,625][00119] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-23 13:44:31,626][00119] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-23 13:44:31,627][00119] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 13:44:31,628][00119] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 13:44:31,629][00119] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 13:44:31,630][00119] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 13:44:31,631][00119] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 13:44:31,659][00119] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 13:44:31,663][00119] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 13:44:31,668][00119] RunningMeanStd input shape: (1,) | |
| [2023-02-23 13:44:31,684][00119] ConvEncoder: input_channels=3 | |
| [2023-02-23 13:44:32,369][00119] Conv encoder output size: 512 | |
| [2023-02-23 13:44:32,370][00119] Policy head output size: 512 | |
| [2023-02-23 13:44:34,869][00119] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 13:44:36,108][00119] Num frames 100... | |
| [2023-02-23 13:44:36,227][00119] Num frames 200... | |
| [2023-02-23 13:44:36,343][00119] Num frames 300... | |
| [2023-02-23 13:44:36,457][00119] Num frames 400... | |
| [2023-02-23 13:44:36,567][00119] Num frames 500... | |
| [2023-02-23 13:44:36,680][00119] Num frames 600... | |
| [2023-02-23 13:44:36,805][00119] Num frames 700... | |
| [2023-02-23 13:44:36,930][00119] Num frames 800... | |
| [2023-02-23 13:44:37,041][00119] Num frames 900... | |
| [2023-02-23 13:44:37,152][00119] Num frames 1000... | |
| [2023-02-23 13:44:37,262][00119] Num frames 1100... | |
| [2023-02-23 13:44:37,372][00119] Num frames 1200... | |
| [2023-02-23 13:44:37,489][00119] Num frames 1300... | |
| [2023-02-23 13:44:37,600][00119] Num frames 1400... | |
| [2023-02-23 13:44:37,725][00119] Num frames 1500... | |
| [2023-02-23 13:44:37,837][00119] Num frames 1600... | |
| [2023-02-23 13:44:37,946][00119] Num frames 1700... | |
| [2023-02-23 13:44:38,085][00119] Avg episode rewards: #0: 46.649, true rewards: #0: 17.650 | |
| [2023-02-23 13:44:38,087][00119] Avg episode reward: 46.649, avg true_objective: 17.650 | |
| [2023-02-23 13:44:38,205][00119] Num frames 1800... | |
| [2023-02-23 13:44:38,466][00119] Num frames 1900... | |
| [2023-02-23 13:44:38,756][00119] Num frames 2000... | |
| [2023-02-23 13:44:39,026][00119] Num frames 2100... | |
| [2023-02-23 13:44:39,382][00119] Num frames 2200... | |
| [2023-02-23 13:44:39,715][00119] Num frames 2300... | |
| [2023-02-23 13:44:40,056][00119] Num frames 2400... | |
| [2023-02-23 13:44:40,424][00119] Num frames 2500... | |
| [2023-02-23 13:44:40,761][00119] Num frames 2600... | |
| [2023-02-23 13:44:41,092][00119] Num frames 2700... | |
| [2023-02-23 13:44:41,523][00119] Num frames 2800... | |
| [2023-02-23 13:44:41,801][00119] Num frames 2900... | |
| [2023-02-23 13:44:41,858][00119] Avg episode rewards: #0: 38.000, true rewards: #0: 14.500 | |
| [2023-02-23 13:44:41,860][00119] Avg episode reward: 38.000, avg true_objective: 14.500 | |
| [2023-02-23 13:44:42,142][00119] Num frames 3000... | |
| [2023-02-23 13:44:42,484][00119] Num frames 3100... | |
| [2023-02-23 13:44:42,851][00119] Num frames 3200... | |
| [2023-02-23 13:44:43,111][00119] Num frames 3300... | |
| [2023-02-23 13:44:43,338][00119] Num frames 3400... | |
| [2023-02-23 13:44:43,499][00119] Num frames 3500... | |
| [2023-02-23 13:44:43,670][00119] Num frames 3600... | |
| [2023-02-23 13:44:43,937][00119] Num frames 3700... | |
| [2023-02-23 13:44:44,141][00119] Num frames 3800... | |
| [2023-02-23 13:44:44,308][00119] Num frames 3900... | |
| [2023-02-23 13:44:44,536][00119] Num frames 4000... | |
| [2023-02-23 13:44:44,812][00119] Num frames 4100... | |
| [2023-02-23 13:44:45,092][00119] Num frames 4200... | |
| [2023-02-23 13:44:45,311][00119] Num frames 4300... | |
| [2023-02-23 13:44:45,504][00119] Num frames 4400... | |
| [2023-02-23 13:44:45,765][00119] Avg episode rewards: #0: 38.273, true rewards: #0: 14.940 | |
| [2023-02-23 13:44:45,772][00119] Avg episode reward: 38.273, avg true_objective: 14.940 | |
| [2023-02-23 13:44:45,809][00119] Num frames 4500... | |
| [2023-02-23 13:44:46,078][00119] Num frames 4600... | |
| [2023-02-23 13:44:46,275][00119] Num frames 4700... | |
| [2023-02-23 13:44:46,389][00119] Num frames 4800... | |
| [2023-02-23 13:44:46,503][00119] Num frames 4900... | |
| [2023-02-23 13:44:46,628][00119] Num frames 5000... | |
| [2023-02-23 13:44:46,740][00119] Num frames 5100... | |
| [2023-02-23 13:44:46,854][00119] Num frames 5200... | |
| [2023-02-23 13:44:46,978][00119] Num frames 5300... | |
| [2023-02-23 13:44:47,094][00119] Num frames 5400... | |
| [2023-02-23 13:44:47,206][00119] Num frames 5500... | |
| [2023-02-23 13:44:47,320][00119] Num frames 5600... | |
| [2023-02-23 13:44:47,429][00119] Num frames 5700... | |
| [2023-02-23 13:44:47,537][00119] Num frames 5800... | |
| [2023-02-23 13:44:47,658][00119] Num frames 5900... | |
| [2023-02-23 13:44:47,771][00119] Num frames 6000... | |
| [2023-02-23 13:44:47,883][00119] Num frames 6100... | |
| [2023-02-23 13:44:47,994][00119] Avg episode rewards: #0: 39.615, true rewards: #0: 15.365 | |
| [2023-02-23 13:44:47,996][00119] Avg episode reward: 39.615, avg true_objective: 15.365 | |
| [2023-02-23 13:44:48,066][00119] Num frames 6200... | |
| [2023-02-23 13:44:48,175][00119] Num frames 6300... | |
| [2023-02-23 13:44:48,283][00119] Num frames 6400... | |
| [2023-02-23 13:44:48,393][00119] Num frames 6500... | |
| [2023-02-23 13:44:48,512][00119] Num frames 6600... | |
| [2023-02-23 13:44:48,623][00119] Num frames 6700... | |
| [2023-02-23 13:44:48,732][00119] Num frames 6800... | |
| [2023-02-23 13:44:48,849][00119] Num frames 6900... | |
| [2023-02-23 13:44:48,974][00119] Num frames 7000... | |
| [2023-02-23 13:44:49,086][00119] Num frames 7100... | |
| [2023-02-23 13:44:49,223][00119] Avg episode rewards: #0: 35.940, true rewards: #0: 14.340 | |
| [2023-02-23 13:44:49,225][00119] Avg episode reward: 35.940, avg true_objective: 14.340 | |
| [2023-02-23 13:44:49,260][00119] Num frames 7200... | |
| [2023-02-23 13:44:49,378][00119] Num frames 7300... | |
| [2023-02-23 13:44:49,486][00119] Num frames 7400... | |
| [2023-02-23 13:44:49,600][00119] Num frames 7500... | |
| [2023-02-23 13:44:49,709][00119] Num frames 7600... | |
| [2023-02-23 13:44:49,822][00119] Num frames 7700... | |
| [2023-02-23 13:44:49,937][00119] Num frames 7800... | |
| [2023-02-23 13:44:50,053][00119] Num frames 7900... | |
| [2023-02-23 13:44:50,165][00119] Num frames 8000... | |
| [2023-02-23 13:44:50,276][00119] Num frames 8100... | |
| [2023-02-23 13:44:50,388][00119] Num frames 8200... | |
| [2023-02-23 13:44:50,462][00119] Avg episode rewards: #0: 33.525, true rewards: #0: 13.692 | |
| [2023-02-23 13:44:50,464][00119] Avg episode reward: 33.525, avg true_objective: 13.692 | |
| [2023-02-23 13:44:50,557][00119] Num frames 8300... | |
| [2023-02-23 13:44:50,683][00119] Num frames 8400... | |
| [2023-02-23 13:44:50,794][00119] Num frames 8500... | |
| [2023-02-23 13:44:50,904][00119] Num frames 8600... | |
| [2023-02-23 13:44:51,026][00119] Num frames 8700... | |
| [2023-02-23 13:44:51,145][00119] Num frames 8800... | |
| [2023-02-23 13:44:51,253][00119] Num frames 8900... | |
| [2023-02-23 13:44:51,367][00119] Num frames 9000... | |
| [2023-02-23 13:44:51,477][00119] Num frames 9100... | |
| [2023-02-23 13:44:51,546][00119] Avg episode rewards: #0: 31.016, true rewards: #0: 13.016 | |
| [2023-02-23 13:44:51,547][00119] Avg episode reward: 31.016, avg true_objective: 13.016 | |
| [2023-02-23 13:44:51,653][00119] Num frames 9200... | |
| [2023-02-23 13:44:51,760][00119] Num frames 9300... | |
| [2023-02-23 13:44:51,873][00119] Num frames 9400... | |
| [2023-02-23 13:44:51,986][00119] Num frames 9500... | |
| [2023-02-23 13:44:52,101][00119] Num frames 9600... | |
| [2023-02-23 13:44:52,215][00119] Num frames 9700... | |
| [2023-02-23 13:44:52,324][00119] Num frames 9800... | |
| [2023-02-23 13:44:52,432][00119] Num frames 9900... | |
| [2023-02-23 13:44:52,540][00119] Num frames 10000... | |
| [2023-02-23 13:44:52,655][00119] Num frames 10100... | |
| [2023-02-23 13:44:52,776][00119] Num frames 10200... | |
| [2023-02-23 13:44:52,941][00119] Num frames 10300... | |
| [2023-02-23 13:44:53,041][00119] Avg episode rewards: #0: 31.034, true rewards: #0: 12.909 | |
| [2023-02-23 13:44:53,044][00119] Avg episode reward: 31.034, avg true_objective: 12.909 | |
| [2023-02-23 13:44:53,159][00119] Num frames 10400... | |
| [2023-02-23 13:44:53,310][00119] Num frames 10500... | |
| [2023-02-23 13:44:53,462][00119] Num frames 10600... | |
| [2023-02-23 13:44:53,615][00119] Num frames 10700... | |
| [2023-02-23 13:44:53,770][00119] Num frames 10800... | |
| [2023-02-23 13:44:53,943][00119] Num frames 10900... | |
| [2023-02-23 13:44:54,124][00119] Num frames 11000... | |
| [2023-02-23 13:44:54,287][00119] Num frames 11100... | |
| [2023-02-23 13:44:54,439][00119] Num frames 11200... | |
| [2023-02-23 13:44:54,604][00119] Num frames 11300... | |
| [2023-02-23 13:44:54,767][00119] Num frames 11400... | |
| [2023-02-23 13:44:54,930][00119] Num frames 11500... | |
| [2023-02-23 13:44:55,088][00119] Num frames 11600... | |
| [2023-02-23 13:44:55,255][00119] Num frames 11700... | |
| [2023-02-23 13:44:55,420][00119] Num frames 11800... | |
| [2023-02-23 13:44:55,579][00119] Num frames 11900... | |
| [2023-02-23 13:44:55,741][00119] Num frames 12000... | |
| [2023-02-23 13:44:55,908][00119] Num frames 12100... | |
| [2023-02-23 13:44:56,065][00119] Num frames 12200... | |
| [2023-02-23 13:44:56,228][00119] Num frames 12300... | |
| [2023-02-23 13:44:56,381][00119] Num frames 12400... | |
| [2023-02-23 13:44:56,466][00119] Avg episode rewards: #0: 33.474, true rewards: #0: 13.808 | |
| [2023-02-23 13:44:56,468][00119] Avg episode reward: 33.474, avg true_objective: 13.808 | |
| [2023-02-23 13:44:56,551][00119] Num frames 12500... | |
| [2023-02-23 13:44:56,665][00119] Num frames 12600... | |
| [2023-02-23 13:44:56,776][00119] Num frames 12700... | |
| [2023-02-23 13:44:56,887][00119] Num frames 12800... | |
| [2023-02-23 13:44:57,002][00119] Num frames 12900... | |
| [2023-02-23 13:44:57,120][00119] Num frames 13000... | |
| [2023-02-23 13:44:57,235][00119] Num frames 13100... | |
| [2023-02-23 13:44:57,345][00119] Num frames 13200... | |
| [2023-02-23 13:44:57,468][00119] Avg episode rewards: #0: 31.759, true rewards: #0: 13.259 | |
| [2023-02-23 13:44:57,470][00119] Avg episode reward: 31.759, avg true_objective: 13.259 | |
| [2023-02-23 13:46:15,099][00119] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-23 13:47:46,954][00119] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 13:47:46,959][00119] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 13:47:46,964][00119] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 13:47:46,967][00119] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 13:47:46,973][00119] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 13:47:46,974][00119] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 13:47:46,975][00119] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-23 13:47:46,977][00119] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 13:47:46,978][00119] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-23 13:47:46,982][00119] Adding new argument 'hf_repository'='tayfen/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-23 13:47:46,983][00119] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 13:47:46,984][00119] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 13:47:46,985][00119] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 13:47:46,987][00119] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 13:47:46,988][00119] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 13:47:47,024][00119] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 13:47:47,027][00119] RunningMeanStd input shape: (1,) | |
| [2023-02-23 13:47:47,050][00119] ConvEncoder: input_channels=3 | |
| [2023-02-23 13:47:47,107][00119] Conv encoder output size: 512 | |
| [2023-02-23 13:47:47,110][00119] Policy head output size: 512 | |
| [2023-02-23 13:47:47,138][00119] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 13:47:47,641][00119] Num frames 100... | |
| [2023-02-23 13:47:47,758][00119] Num frames 200... | |
| [2023-02-23 13:47:47,867][00119] Num frames 300... | |
| [2023-02-23 13:47:47,976][00119] Num frames 400... | |
| [2023-02-23 13:47:48,084][00119] Num frames 500... | |
| [2023-02-23 13:47:48,196][00119] Num frames 600... | |
| [2023-02-23 13:47:48,303][00119] Num frames 700... | |
| [2023-02-23 13:47:48,418][00119] Num frames 800... | |
| [2023-02-23 13:47:48,528][00119] Num frames 900... | |
| [2023-02-23 13:47:48,646][00119] Num frames 1000... | |
| [2023-02-23 13:47:48,757][00119] Num frames 1100... | |
| [2023-02-23 13:47:48,835][00119] Avg episode rewards: #0: 31.200, true rewards: #0: 11.200 | |
| [2023-02-23 13:47:48,839][00119] Avg episode reward: 31.200, avg true_objective: 11.200 | |
| [2023-02-23 13:47:48,940][00119] Num frames 1200... | |
| [2023-02-23 13:47:49,051][00119] Num frames 1300... | |
| [2023-02-23 13:47:49,165][00119] Num frames 1400... | |
| [2023-02-23 13:47:49,290][00119] Num frames 1500... | |
| [2023-02-23 13:47:49,399][00119] Num frames 1600... | |
| [2023-02-23 13:47:49,513][00119] Num frames 1700... | |
| [2023-02-23 13:47:49,600][00119] Avg episode rewards: #0: 21.640, true rewards: #0: 8.640 | |
| [2023-02-23 13:47:49,601][00119] Avg episode reward: 21.640, avg true_objective: 8.640 | |
| [2023-02-23 13:47:49,683][00119] Num frames 1800... | |
| [2023-02-23 13:47:49,799][00119] Num frames 1900... | |
| [2023-02-23 13:47:49,909][00119] Num frames 2000... | |
| [2023-02-23 13:47:50,017][00119] Num frames 2100... | |
| [2023-02-23 13:47:50,126][00119] Num frames 2200... | |
| [2023-02-23 13:47:50,238][00119] Num frames 2300... | |
| [2023-02-23 13:47:50,348][00119] Num frames 2400... | |
| [2023-02-23 13:47:50,467][00119] Num frames 2500... | |
| [2023-02-23 13:47:50,590][00119] Num frames 2600... | |
| [2023-02-23 13:47:50,702][00119] Num frames 2700... | |
| [2023-02-23 13:47:50,814][00119] Num frames 2800... | |
| [2023-02-23 13:47:50,936][00119] Num frames 2900... | |
| [2023-02-23 13:47:51,050][00119] Num frames 3000... | |
| [2023-02-23 13:47:51,163][00119] Num frames 3100... | |
| [2023-02-23 13:47:51,281][00119] Num frames 3200... | |
| [2023-02-23 13:47:51,392][00119] Num frames 3300... | |
| [2023-02-23 13:47:51,517][00119] Num frames 3400... | |
| [2023-02-23 13:47:51,631][00119] Num frames 3500... | |
| [2023-02-23 13:47:51,743][00119] Num frames 3600... | |
| [2023-02-23 13:47:51,856][00119] Num frames 3700... | |
| [2023-02-23 13:47:51,975][00119] Num frames 3800... | |
| [2023-02-23 13:47:52,062][00119] Avg episode rewards: #0: 31.760, true rewards: #0: 12.760 | |
| [2023-02-23 13:47:52,063][00119] Avg episode reward: 31.760, avg true_objective: 12.760 | |
| [2023-02-23 13:47:52,145][00119] Num frames 3900... | |
| [2023-02-23 13:47:52,254][00119] Num frames 4000... | |
| [2023-02-23 13:47:52,369][00119] Num frames 4100... | |
| [2023-02-23 13:47:52,481][00119] Num frames 4200... | |
| [2023-02-23 13:47:52,601][00119] Num frames 4300... | |
| [2023-02-23 13:47:52,712][00119] Num frames 4400... | |
| [2023-02-23 13:47:52,845][00119] Avg episode rewards: #0: 26.670, true rewards: #0: 11.170 | |
| [2023-02-23 13:47:52,846][00119] Avg episode reward: 26.670, avg true_objective: 11.170 | |
| [2023-02-23 13:47:52,894][00119] Num frames 4500... | |
| [2023-02-23 13:47:53,010][00119] Num frames 4600... | |
| [2023-02-23 13:47:53,128][00119] Num frames 4700... | |
| [2023-02-23 13:47:53,238][00119] Num frames 4800... | |
| [2023-02-23 13:47:53,356][00119] Num frames 4900... | |
| [2023-02-23 13:47:53,467][00119] Num frames 5000... | |
| [2023-02-23 13:47:53,616][00119] Avg episode rewards: #0: 23.352, true rewards: #0: 10.152 | |
| [2023-02-23 13:47:53,618][00119] Avg episode reward: 23.352, avg true_objective: 10.152 | |
| [2023-02-23 13:47:53,648][00119] Num frames 5100... | |
| [2023-02-23 13:47:53,759][00119] Num frames 5200... | |
| [2023-02-23 13:47:53,867][00119] Num frames 5300... | |
| [2023-02-23 13:47:53,982][00119] Num frames 5400... | |
| [2023-02-23 13:47:54,091][00119] Num frames 5500... | |
| [2023-02-23 13:47:54,211][00119] Num frames 5600... | |
| [2023-02-23 13:47:54,333][00119] Num frames 5700... | |
| [2023-02-23 13:47:54,451][00119] Num frames 5800... | |
| [2023-02-23 13:47:54,573][00119] Num frames 5900... | |
| [2023-02-23 13:47:54,692][00119] Num frames 6000... | |
| [2023-02-23 13:47:54,804][00119] Num frames 6100... | |
| [2023-02-23 13:47:54,927][00119] Num frames 6200... | |
| [2023-02-23 13:47:55,040][00119] Num frames 6300... | |
| [2023-02-23 13:47:55,155][00119] Num frames 6400... | |
| [2023-02-23 13:47:55,271][00119] Num frames 6500... | |
| [2023-02-23 13:47:55,383][00119] Num frames 6600... | |
| [2023-02-23 13:47:55,495][00119] Num frames 6700... | |
| [2023-02-23 13:47:55,619][00119] Num frames 6800... | |
| [2023-02-23 13:47:55,731][00119] Num frames 6900... | |
| [2023-02-23 13:47:55,853][00119] Num frames 7000... | |
| [2023-02-23 13:47:55,963][00119] Num frames 7100... | |
| [2023-02-23 13:47:56,101][00119] Avg episode rewards: #0: 28.793, true rewards: #0: 11.960 | |
| [2023-02-23 13:47:56,102][00119] Avg episode reward: 28.793, avg true_objective: 11.960 | |
| [2023-02-23 13:47:56,133][00119] Num frames 7200... | |
| [2023-02-23 13:47:56,247][00119] Num frames 7300... | |
| [2023-02-23 13:47:56,356][00119] Num frames 7400... | |
| [2023-02-23 13:47:56,467][00119] Num frames 7500... | |
| [2023-02-23 13:47:56,584][00119] Num frames 7600... | |
| [2023-02-23 13:47:56,705][00119] Num frames 7700... | |
| [2023-02-23 13:47:56,825][00119] Num frames 7800... | |
| [2023-02-23 13:47:56,946][00119] Num frames 7900... | |
| [2023-02-23 13:47:57,070][00119] Num frames 8000... | |
| [2023-02-23 13:47:57,181][00119] Num frames 8100... | |
| [2023-02-23 13:47:57,295][00119] Num frames 8200... | |
| [2023-02-23 13:47:57,441][00119] Num frames 8300... | |
| [2023-02-23 13:47:57,616][00119] Num frames 8400... | |
| [2023-02-23 13:47:57,770][00119] Num frames 8500... | |
| [2023-02-23 13:47:57,925][00119] Num frames 8600... | |
| [2023-02-23 13:47:58,075][00119] Num frames 8700... | |
| [2023-02-23 13:47:58,230][00119] Num frames 8800... | |
| [2023-02-23 13:47:58,359][00119] Avg episode rewards: #0: 30.780, true rewards: #0: 12.637 | |
| [2023-02-23 13:47:58,362][00119] Avg episode reward: 30.780, avg true_objective: 12.637 | |
| [2023-02-23 13:47:58,444][00119] Num frames 8900... | |
| [2023-02-23 13:47:58,602][00119] Num frames 9000... | |
| [2023-02-23 13:47:58,760][00119] Num frames 9100... | |
| [2023-02-23 13:47:58,910][00119] Num frames 9200... | |
| [2023-02-23 13:47:59,061][00119] Num frames 9300... | |
| [2023-02-23 13:47:59,220][00119] Num frames 9400... | |
| [2023-02-23 13:47:59,317][00119] Avg episode rewards: #0: 28.277, true rewards: #0: 11.778 | |
| [2023-02-23 13:47:59,319][00119] Avg episode reward: 28.277, avg true_objective: 11.778 | |
| [2023-02-23 13:47:59,438][00119] Num frames 9500... | |
| [2023-02-23 13:47:59,594][00119] Num frames 9600... | |
| [2023-02-23 13:47:59,759][00119] Num frames 9700... | |
| [2023-02-23 13:47:59,918][00119] Num frames 9800... | |
| [2023-02-23 13:48:00,074][00119] Num frames 9900... | |
| [2023-02-23 13:48:00,234][00119] Num frames 10000... | |
| [2023-02-23 13:48:00,395][00119] Num frames 10100... | |
| [2023-02-23 13:48:00,551][00119] Num frames 10200... | |
| [2023-02-23 13:48:00,740][00119] Avg episode rewards: #0: 26.754, true rewards: #0: 11.421 | |
| [2023-02-23 13:48:00,742][00119] Avg episode reward: 26.754, avg true_objective: 11.421 | |
| [2023-02-23 13:48:00,776][00119] Num frames 10300... | |
| [2023-02-23 13:48:00,899][00119] Num frames 10400... | |
| [2023-02-23 13:48:01,010][00119] Num frames 10500... | |
| [2023-02-23 13:48:01,121][00119] Num frames 10600... | |
| [2023-02-23 13:48:01,237][00119] Num frames 10700... | |
| [2023-02-23 13:48:01,347][00119] Num frames 10800... | |
| [2023-02-23 13:48:01,463][00119] Num frames 10900... | |
| [2023-02-23 13:48:01,580][00119] Num frames 11000... | |
| [2023-02-23 13:48:01,693][00119] Num frames 11100... | |
| [2023-02-23 13:48:01,812][00119] Num frames 11200... | |
| [2023-02-23 13:48:01,922][00119] Num frames 11300... | |
| [2023-02-23 13:48:02,034][00119] Num frames 11400... | |
| [2023-02-23 13:48:02,136][00119] Avg episode rewards: #0: 26.438, true rewards: #0: 11.438 | |
| [2023-02-23 13:48:02,138][00119] Avg episode reward: 26.438, avg true_objective: 11.438 | |
| [2023-02-23 13:49:08,215][00119] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |