| [2023-02-24 16:53:48,512][08483] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-24 16:53:48,516][08483] Rollout worker 0 uses device cpu | |
| [2023-02-24 16:53:48,517][08483] Rollout worker 1 uses device cpu | |
| [2023-02-24 16:53:48,523][08483] Rollout worker 2 uses device cpu | |
| [2023-02-24 16:53:48,524][08483] Rollout worker 3 uses device cpu | |
| [2023-02-24 16:53:48,529][08483] Rollout worker 4 uses device cpu | |
| [2023-02-24 16:53:48,530][08483] Rollout worker 5 uses device cpu | |
| [2023-02-24 16:53:48,533][08483] Rollout worker 6 uses device cpu | |
| [2023-02-24 16:53:48,536][08483] Rollout worker 7 uses device cpu | |
| [2023-02-24 16:53:48,719][08483] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 16:53:48,722][08483] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-24 16:53:48,757][08483] Starting all processes... | |
| [2023-02-24 16:53:48,759][08483] Starting process learner_proc0 | |
| [2023-02-24 16:53:48,819][08483] Starting all processes... | |
| [2023-02-24 16:53:48,830][08483] Starting process inference_proc0-0 | |
| [2023-02-24 16:53:48,831][08483] Starting process rollout_proc0 | |
| [2023-02-24 16:53:48,832][08483] Starting process rollout_proc1 | |
| [2023-02-24 16:53:48,833][08483] Starting process rollout_proc2 | |
| [2023-02-24 16:53:48,833][08483] Starting process rollout_proc3 | |
| [2023-02-24 16:53:48,834][08483] Starting process rollout_proc4 | |
| [2023-02-24 16:53:48,834][08483] Starting process rollout_proc5 | |
| [2023-02-24 16:53:48,834][08483] Starting process rollout_proc6 | |
| [2023-02-24 16:53:48,834][08483] Starting process rollout_proc7 | |
| [2023-02-24 16:53:57,937][14191] Worker 7 uses CPU cores [1] | |
| [2023-02-24 16:53:58,628][14184] Worker 0 uses CPU cores [0] | |
| [2023-02-24 16:53:58,633][14169] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 16:53:58,634][14169] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-24 16:53:58,674][14186] Worker 2 uses CPU cores [0] | |
| [2023-02-24 16:53:58,745][14185] Worker 1 uses CPU cores [1] | |
| [2023-02-24 16:53:58,755][14188] Worker 5 uses CPU cores [1] | |
| [2023-02-24 16:53:58,780][14183] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 16:53:58,780][14183] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-24 16:53:58,797][14189] Worker 3 uses CPU cores [1] | |
| [2023-02-24 16:53:58,810][14187] Worker 4 uses CPU cores [0] | |
| [2023-02-24 16:53:58,908][14190] Worker 6 uses CPU cores [0] | |
| [2023-02-24 16:53:59,419][14183] Num visible devices: 1 | |
| [2023-02-24 16:53:59,423][14169] Num visible devices: 1 | |
| [2023-02-24 16:53:59,438][14169] Starting seed is not provided | |
| [2023-02-24 16:53:59,438][14169] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 16:53:59,439][14169] Initializing actor-critic model on device cuda:0 | |
| [2023-02-24 16:53:59,439][14169] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 16:53:59,441][14169] RunningMeanStd input shape: (1,) | |
| [2023-02-24 16:53:59,461][14169] ConvEncoder: input_channels=3 | |
| [2023-02-24 16:53:59,781][14169] Conv encoder output size: 512 | |
| [2023-02-24 16:53:59,782][14169] Policy head output size: 512 | |
| [2023-02-24 16:53:59,842][14169] Created Actor Critic model with architecture: | |
| [2023-02-24 16:53:59,842][14169] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2023-02-24 16:54:06,751][14169] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-24 16:54:06,752][14169] No checkpoints found | |
| [2023-02-24 16:54:06,752][14169] Did not load from checkpoint, starting from scratch! | |
| [2023-02-24 16:54:06,753][14169] Initialized policy 0 weights for model version 0 | |
| [2023-02-24 16:54:06,757][14169] LearnerWorker_p0 finished initialization! | |
| [2023-02-24 16:54:06,761][14169] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-24 16:54:06,960][14183] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 16:54:06,962][14183] RunningMeanStd input shape: (1,) | |
| [2023-02-24 16:54:06,978][14183] ConvEncoder: input_channels=3 | |
| [2023-02-24 16:54:07,073][14183] Conv encoder output size: 512 | |
| [2023-02-24 16:54:07,073][14183] Policy head output size: 512 | |
| [2023-02-24 16:54:08,711][08483] Heartbeat connected on Batcher_0 | |
| [2023-02-24 16:54:08,720][08483] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-24 16:54:08,722][08483] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 16:54:08,732][08483] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-24 16:54:08,737][08483] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-24 16:54:08,744][08483] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-24 16:54:08,762][08483] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-24 16:54:08,763][08483] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-24 16:54:08,766][08483] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-24 16:54:08,767][08483] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-24 16:54:08,770][08483] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-24 16:54:09,282][08483] Inference worker 0-0 is ready! | |
| [2023-02-24 16:54:09,284][08483] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-24 16:54:09,295][08483] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-24 16:54:09,398][14190] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,408][14186] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,412][14187] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,444][14184] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,451][14191] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,449][14188] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,458][14189] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:09,459][14185] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 16:54:10,267][14188] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:10,269][14185] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:10,603][14188] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:10,778][14190] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:10,780][14186] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:10,786][14187] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:10,807][14184] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:11,428][14185] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:11,564][14191] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:12,162][14187] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:12,167][14186] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:12,175][14190] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:12,203][14184] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:13,270][14189] Decorrelating experience for 0 frames... | |
| [2023-02-24 16:54:13,385][14191] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:13,628][14185] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:13,717][08483] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 16:54:14,061][14187] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:14,083][14190] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:14,747][14186] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:15,062][14184] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:15,261][14190] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:15,597][14189] Decorrelating experience for 32 frames... | |
| [2023-02-24 16:54:15,843][14188] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:16,214][14185] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:16,805][14191] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:17,528][14188] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:17,656][14189] Decorrelating experience for 64 frames... | |
| [2023-02-24 16:54:17,945][14191] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:18,260][14184] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:18,313][14189] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:18,652][14187] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:18,721][08483] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 16:54:19,079][14186] Decorrelating experience for 96 frames... | |
| [2023-02-24 16:54:22,729][14169] Signal inference workers to stop experience collection... | |
| [2023-02-24 16:54:22,746][14183] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-24 16:54:23,717][08483] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 85.4. Samples: 1280. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-24 16:54:23,720][08483] Avg episode reward: [(0, '2.019')] | |
| [2023-02-24 16:54:25,140][14169] Signal inference workers to resume experience collection... | |
| [2023-02-24 16:54:25,143][14183] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-24 16:54:28,717][08483] Fps is (10 sec: 2048.7, 60 sec: 1024.2, 300 sec: 1024.2). Total num frames: 20480. Throughput: 0: 201.9. Samples: 4038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:54:28,725][08483] Avg episode reward: [(0, '3.556')] | |
| [2023-02-24 16:54:33,717][08483] Fps is (10 sec: 3686.4, 60 sec: 1474.8, 300 sec: 1474.8). Total num frames: 36864. Throughput: 0: 387.2. Samples: 9678. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-24 16:54:33,726][08483] Avg episode reward: [(0, '3.984')] | |
| [2023-02-24 16:54:34,602][14183] Updated weights for policy 0, policy_version 10 (0.0344) | |
| [2023-02-24 16:54:38,718][08483] Fps is (10 sec: 2867.0, 60 sec: 1638.6, 300 sec: 1638.6). Total num frames: 49152. Throughput: 0: 397.9. Samples: 11936. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:54:38,721][08483] Avg episode reward: [(0, '4.402')] | |
| [2023-02-24 16:54:43,717][08483] Fps is (10 sec: 3686.4, 60 sec: 2106.8, 300 sec: 2106.8). Total num frames: 73728. Throughput: 0: 496.8. Samples: 17386. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-24 16:54:43,720][08483] Avg episode reward: [(0, '4.423')] | |
| [2023-02-24 16:54:45,419][14183] Updated weights for policy 0, policy_version 20 (0.0014) | |
| [2023-02-24 16:54:48,720][08483] Fps is (10 sec: 4504.7, 60 sec: 2355.3, 300 sec: 2355.3). Total num frames: 94208. Throughput: 0: 611.2. Samples: 24446. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-24 16:54:48,727][08483] Avg episode reward: [(0, '4.278')] | |
| [2023-02-24 16:54:53,718][08483] Fps is (10 sec: 4096.0, 60 sec: 2548.9, 300 sec: 2548.9). Total num frames: 114688. Throughput: 0: 608.2. Samples: 27368. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-24 16:54:53,720][08483] Avg episode reward: [(0, '4.331')] | |
| [2023-02-24 16:54:53,728][14169] Saving new best policy, reward=4.331! | |
| [2023-02-24 16:54:56,271][14183] Updated weights for policy 0, policy_version 30 (0.0025) | |
| [2023-02-24 16:54:58,717][08483] Fps is (10 sec: 3277.7, 60 sec: 2539.7, 300 sec: 2539.7). Total num frames: 126976. Throughput: 0: 709.6. Samples: 31934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:54:58,721][08483] Avg episode reward: [(0, '4.432')] | |
| [2023-02-24 16:54:58,801][14169] Saving new best policy, reward=4.432! | |
| [2023-02-24 16:55:03,717][08483] Fps is (10 sec: 3686.4, 60 sec: 2755.7, 300 sec: 2755.7). Total num frames: 151552. Throughput: 0: 850.0. Samples: 38248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:55:03,720][08483] Avg episode reward: [(0, '4.234')] | |
| [2023-02-24 16:55:06,182][14183] Updated weights for policy 0, policy_version 40 (0.0020) | |
| [2023-02-24 16:55:08,717][08483] Fps is (10 sec: 4915.2, 60 sec: 2935.7, 300 sec: 2935.7). Total num frames: 176128. Throughput: 0: 898.8. Samples: 41724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:55:08,725][08483] Avg episode reward: [(0, '4.422')] | |
| [2023-02-24 16:55:13,723][08483] Fps is (10 sec: 4093.6, 60 sec: 3208.2, 300 sec: 2961.7). Total num frames: 192512. Throughput: 0: 968.6. Samples: 47632. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:55:13,730][08483] Avg episode reward: [(0, '4.527')] | |
| [2023-02-24 16:55:13,740][14169] Saving new best policy, reward=4.527! | |
| [2023-02-24 16:55:17,805][14183] Updated weights for policy 0, policy_version 50 (0.0020) | |
| [2023-02-24 16:55:18,718][08483] Fps is (10 sec: 2867.0, 60 sec: 3413.5, 300 sec: 2925.9). Total num frames: 204800. Throughput: 0: 941.0. Samples: 52026. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:55:18,725][08483] Avg episode reward: [(0, '4.435')] | |
| [2023-02-24 16:55:23,717][08483] Fps is (10 sec: 3688.6, 60 sec: 3822.9, 300 sec: 3058.5). Total num frames: 229376. Throughput: 0: 958.2. Samples: 55056. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:55:23,725][08483] Avg episode reward: [(0, '4.531')] | |
| [2023-02-24 16:55:23,735][14169] Saving new best policy, reward=4.531! | |
| [2023-02-24 16:55:27,171][14183] Updated weights for policy 0, policy_version 60 (0.0014) | |
| [2023-02-24 16:55:28,717][08483] Fps is (10 sec: 4506.0, 60 sec: 3822.9, 300 sec: 3123.4). Total num frames: 249856. Throughput: 0: 993.6. Samples: 62098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:55:28,719][08483] Avg episode reward: [(0, '4.470')] | |
| [2023-02-24 16:55:33,721][08483] Fps is (10 sec: 3685.0, 60 sec: 3822.7, 300 sec: 3132.3). Total num frames: 266240. Throughput: 0: 961.8. Samples: 67728. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:55:33,724][08483] Avg episode reward: [(0, '4.778')] | |
| [2023-02-24 16:55:33,734][14169] Saving new best policy, reward=4.778! | |
| [2023-02-24 16:55:38,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3140.4). Total num frames: 282624. Throughput: 0: 947.3. Samples: 69996. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:55:38,725][08483] Avg episode reward: [(0, '4.628')] | |
| [2023-02-24 16:55:39,125][14183] Updated weights for policy 0, policy_version 70 (0.0023) | |
| [2023-02-24 16:55:43,717][08483] Fps is (10 sec: 4097.5, 60 sec: 3891.2, 300 sec: 3233.8). Total num frames: 307200. Throughput: 0: 976.0. Samples: 75856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 16:55:43,725][08483] Avg episode reward: [(0, '4.270')] | |
| [2023-02-24 16:55:43,737][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000075_307200.pth... | |
| [2023-02-24 16:55:47,973][14183] Updated weights for policy 0, policy_version 80 (0.0016) | |
| [2023-02-24 16:55:48,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3891.4, 300 sec: 3276.9). Total num frames: 327680. Throughput: 0: 990.2. Samples: 82806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:55:48,720][08483] Avg episode reward: [(0, '4.454')] | |
| [2023-02-24 16:55:53,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3276.9). Total num frames: 344064. Throughput: 0: 974.3. Samples: 85566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:55:53,722][08483] Avg episode reward: [(0, '4.569')] | |
| [2023-02-24 16:55:58,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3276.9). Total num frames: 360448. Throughput: 0: 944.0. Samples: 90108. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-24 16:55:58,724][08483] Avg episode reward: [(0, '4.395')] | |
| [2023-02-24 16:56:00,144][14183] Updated weights for policy 0, policy_version 90 (0.0044) | |
| [2023-02-24 16:56:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3348.2). Total num frames: 385024. Throughput: 0: 985.1. Samples: 96356. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:56:03,720][08483] Avg episode reward: [(0, '4.429')] | |
| [2023-02-24 16:56:08,718][08483] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3379.3). Total num frames: 405504. Throughput: 0: 993.6. Samples: 99768. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:56:08,724][08483] Avg episode reward: [(0, '4.436')] | |
| [2023-02-24 16:56:09,028][14183] Updated weights for policy 0, policy_version 100 (0.0017) | |
| [2023-02-24 16:56:13,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3823.3, 300 sec: 3375.2). Total num frames: 421888. Throughput: 0: 961.7. Samples: 105374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:56:13,720][08483] Avg episode reward: [(0, '4.505')] | |
| [2023-02-24 16:56:18,717][08483] Fps is (10 sec: 3276.9, 60 sec: 3891.3, 300 sec: 3371.4). Total num frames: 438272. Throughput: 0: 937.9. Samples: 109930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:56:18,726][08483] Avg episode reward: [(0, '4.534')] | |
| [2023-02-24 16:56:21,304][14183] Updated weights for policy 0, policy_version 110 (0.0026) | |
| [2023-02-24 16:56:23,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3398.3). Total num frames: 458752. Throughput: 0: 960.2. Samples: 113204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:56:23,724][08483] Avg episode reward: [(0, '4.549')] | |
| [2023-02-24 16:56:28,718][08483] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3452.4). Total num frames: 483328. Throughput: 0: 990.7. Samples: 120436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 16:56:28,725][08483] Avg episode reward: [(0, '4.620')] | |
| [2023-02-24 16:56:30,187][14183] Updated weights for policy 0, policy_version 120 (0.0013) | |
| [2023-02-24 16:56:33,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.4, 300 sec: 3446.4). Total num frames: 499712. Throughput: 0: 952.4. Samples: 125662. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:56:33,722][08483] Avg episode reward: [(0, '4.507')] | |
| [2023-02-24 16:56:38,717][08483] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3440.7). Total num frames: 516096. Throughput: 0: 940.4. Samples: 127886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 16:56:38,720][08483] Avg episode reward: [(0, '4.495')] | |
| [2023-02-24 16:56:41,906][14183] Updated weights for policy 0, policy_version 130 (0.0011) | |
| [2023-02-24 16:56:43,720][08483] Fps is (10 sec: 3685.5, 60 sec: 3822.8, 300 sec: 3461.8). Total num frames: 536576. Throughput: 0: 976.5. Samples: 134052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:56:43,725][08483] Avg episode reward: [(0, '4.451')] | |
| [2023-02-24 16:56:48,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3507.3). Total num frames: 561152. Throughput: 0: 995.2. Samples: 141140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:56:48,719][08483] Avg episode reward: [(0, '4.323')] | |
| [2023-02-24 16:56:51,913][14183] Updated weights for policy 0, policy_version 140 (0.0021) | |
| [2023-02-24 16:56:53,717][08483] Fps is (10 sec: 4097.0, 60 sec: 3891.2, 300 sec: 3500.3). Total num frames: 577536. Throughput: 0: 972.0. Samples: 143510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:56:53,720][08483] Avg episode reward: [(0, '4.288')] | |
| [2023-02-24 16:56:58,718][08483] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3493.7). Total num frames: 593920. Throughput: 0: 948.5. Samples: 148058. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:56:58,720][08483] Avg episode reward: [(0, '4.255')] | |
| [2023-02-24 16:57:02,666][14183] Updated weights for policy 0, policy_version 150 (0.0031) | |
| [2023-02-24 16:57:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3534.4). Total num frames: 618496. Throughput: 0: 997.2. Samples: 154806. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:57:03,719][08483] Avg episode reward: [(0, '4.177')] | |
| [2023-02-24 16:57:08,717][08483] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3550.0). Total num frames: 638976. Throughput: 0: 1003.4. Samples: 158356. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:57:08,723][08483] Avg episode reward: [(0, '4.488')] | |
| [2023-02-24 16:57:12,919][14183] Updated weights for policy 0, policy_version 160 (0.0023) | |
| [2023-02-24 16:57:13,720][08483] Fps is (10 sec: 3685.5, 60 sec: 3891.0, 300 sec: 3542.5). Total num frames: 655360. Throughput: 0: 966.9. Samples: 163950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:57:13,725][08483] Avg episode reward: [(0, '4.572')] | |
| [2023-02-24 16:57:18,720][08483] Fps is (10 sec: 3275.9, 60 sec: 3891.0, 300 sec: 3535.5). Total num frames: 671744. Throughput: 0: 950.0. Samples: 168416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:57:18,726][08483] Avg episode reward: [(0, '4.403')] | |
| [2023-02-24 16:57:23,604][14183] Updated weights for policy 0, policy_version 170 (0.0021) | |
| [2023-02-24 16:57:23,720][08483] Fps is (10 sec: 4096.1, 60 sec: 3959.3, 300 sec: 3570.9). Total num frames: 696320. Throughput: 0: 980.0. Samples: 171986. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 16:57:23,721][08483] Avg episode reward: [(0, '4.448')] | |
| [2023-02-24 16:57:28,718][08483] Fps is (10 sec: 4916.1, 60 sec: 3959.4, 300 sec: 3604.5). Total num frames: 720896. Throughput: 0: 1002.5. Samples: 179162. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:57:28,726][08483] Avg episode reward: [(0, '4.427')] | |
| [2023-02-24 16:57:33,717][08483] Fps is (10 sec: 3687.2, 60 sec: 3891.2, 300 sec: 3576.6). Total num frames: 733184. Throughput: 0: 954.3. Samples: 184082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:57:33,720][08483] Avg episode reward: [(0, '4.583')] | |
| [2023-02-24 16:57:34,229][14183] Updated weights for policy 0, policy_version 180 (0.0025) | |
| [2023-02-24 16:57:38,717][08483] Fps is (10 sec: 2867.5, 60 sec: 3891.2, 300 sec: 3569.4). Total num frames: 749568. Throughput: 0: 952.9. Samples: 186392. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:57:38,720][08483] Avg episode reward: [(0, '4.653')] | |
| [2023-02-24 16:57:43,718][08483] Fps is (10 sec: 4095.9, 60 sec: 3959.6, 300 sec: 3600.7). Total num frames: 774144. Throughput: 0: 998.2. Samples: 192976. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:57:43,720][08483] Avg episode reward: [(0, '4.744')] | |
| [2023-02-24 16:57:43,736][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000189_774144.pth... | |
| [2023-02-24 16:57:44,109][14183] Updated weights for policy 0, policy_version 190 (0.0028) | |
| [2023-02-24 16:57:48,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3612.0). Total num frames: 794624. Throughput: 0: 995.5. Samples: 199602. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:57:48,722][08483] Avg episode reward: [(0, '4.803')] | |
| [2023-02-24 16:57:48,730][14169] Saving new best policy, reward=4.803! | |
| [2023-02-24 16:57:53,717][08483] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3604.6). Total num frames: 811008. Throughput: 0: 964.8. Samples: 201770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 16:57:53,722][08483] Avg episode reward: [(0, '4.966')] | |
| [2023-02-24 16:57:53,734][14169] Saving new best policy, reward=4.966! | |
| [2023-02-24 16:57:55,989][14183] Updated weights for policy 0, policy_version 200 (0.0015) | |
| [2023-02-24 16:57:58,717][08483] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3597.4). Total num frames: 827392. Throughput: 0: 942.5. Samples: 206358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:57:58,720][08483] Avg episode reward: [(0, '4.948')] | |
| [2023-02-24 16:58:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3625.5). Total num frames: 851968. Throughput: 0: 999.3. Samples: 213380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 16:58:03,720][08483] Avg episode reward: [(0, '4.874')] | |
| [2023-02-24 16:58:05,306][14183] Updated weights for policy 0, policy_version 210 (0.0016) | |
| [2023-02-24 16:58:08,718][08483] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3635.3). Total num frames: 872448. Throughput: 0: 996.7. Samples: 216834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:08,720][08483] Avg episode reward: [(0, '5.076')] | |
| [2023-02-24 16:58:08,727][14169] Saving new best policy, reward=5.076! | |
| [2023-02-24 16:58:13,723][08483] Fps is (10 sec: 3684.2, 60 sec: 3891.0, 300 sec: 3627.9). Total num frames: 888832. Throughput: 0: 954.2. Samples: 222104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:13,729][08483] Avg episode reward: [(0, '5.060')] | |
| [2023-02-24 16:58:17,392][14183] Updated weights for policy 0, policy_version 220 (0.0041) | |
| [2023-02-24 16:58:18,717][08483] Fps is (10 sec: 3276.9, 60 sec: 3891.4, 300 sec: 3620.9). Total num frames: 905216. Throughput: 0: 950.8. Samples: 226870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:18,723][08483] Avg episode reward: [(0, '4.898')] | |
| [2023-02-24 16:58:23,717][08483] Fps is (10 sec: 4098.4, 60 sec: 3891.3, 300 sec: 3646.3). Total num frames: 929792. Throughput: 0: 979.2. Samples: 230456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:23,725][08483] Avg episode reward: [(0, '4.795')] | |
| [2023-02-24 16:58:25,913][14183] Updated weights for policy 0, policy_version 230 (0.0012) | |
| [2023-02-24 16:58:28,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3655.0). Total num frames: 950272. Throughput: 0: 994.9. Samples: 237748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:58:28,720][08483] Avg episode reward: [(0, '5.140')] | |
| [2023-02-24 16:58:28,722][14169] Saving new best policy, reward=5.140! | |
| [2023-02-24 16:58:33,719][08483] Fps is (10 sec: 3685.9, 60 sec: 3891.1, 300 sec: 3647.8). Total num frames: 966656. Throughput: 0: 949.6. Samples: 242334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:58:33,721][08483] Avg episode reward: [(0, '5.112')] | |
| [2023-02-24 16:58:38,109][14183] Updated weights for policy 0, policy_version 240 (0.0029) | |
| [2023-02-24 16:58:38,720][08483] Fps is (10 sec: 3276.1, 60 sec: 3891.1, 300 sec: 3640.9). Total num frames: 983040. Throughput: 0: 952.4. Samples: 244632. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:38,724][08483] Avg episode reward: [(0, '5.049')] | |
| [2023-02-24 16:58:43,717][08483] Fps is (10 sec: 4096.5, 60 sec: 3891.2, 300 sec: 3664.1). Total num frames: 1007616. Throughput: 0: 1000.1. Samples: 251364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:43,720][08483] Avg episode reward: [(0, '5.272')] | |
| [2023-02-24 16:58:43,728][14169] Saving new best policy, reward=5.272! | |
| [2023-02-24 16:58:46,856][14183] Updated weights for policy 0, policy_version 250 (0.0015) | |
| [2023-02-24 16:58:48,717][08483] Fps is (10 sec: 4506.6, 60 sec: 3891.2, 300 sec: 3671.8). Total num frames: 1028096. Throughput: 0: 987.6. Samples: 257820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:58:48,723][08483] Avg episode reward: [(0, '5.205')] | |
| [2023-02-24 16:58:53,723][08483] Fps is (10 sec: 3684.3, 60 sec: 3890.8, 300 sec: 3664.8). Total num frames: 1044480. Throughput: 0: 962.2. Samples: 260138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:58:53,728][08483] Avg episode reward: [(0, '5.085')] | |
| [2023-02-24 16:58:58,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3658.2). Total num frames: 1060864. Throughput: 0: 948.0. Samples: 264760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:58:58,724][08483] Avg episode reward: [(0, '4.709')] | |
| [2023-02-24 16:58:59,032][14183] Updated weights for policy 0, policy_version 260 (0.0022) | |
| [2023-02-24 16:59:03,718][08483] Fps is (10 sec: 4098.3, 60 sec: 3891.2, 300 sec: 3679.5). Total num frames: 1085440. Throughput: 0: 998.9. Samples: 271820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:59:03,720][08483] Avg episode reward: [(0, '5.093')] | |
| [2023-02-24 16:59:07,814][14183] Updated weights for policy 0, policy_version 270 (0.0016) | |
| [2023-02-24 16:59:08,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 999.2. Samples: 275422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:08,721][08483] Avg episode reward: [(0, '5.493')] | |
| [2023-02-24 16:59:08,722][14169] Saving new best policy, reward=5.493! | |
| [2023-02-24 16:59:13,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3891.6, 300 sec: 3804.5). Total num frames: 1122304. Throughput: 0: 945.3. Samples: 280288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:13,721][08483] Avg episode reward: [(0, '5.401')] | |
| [2023-02-24 16:59:18,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1138688. Throughput: 0: 951.8. Samples: 285166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:18,720][08483] Avg episode reward: [(0, '5.529')] | |
| [2023-02-24 16:59:18,725][14169] Saving new best policy, reward=5.529! | |
| [2023-02-24 16:59:20,286][14183] Updated weights for policy 0, policy_version 280 (0.0014) | |
| [2023-02-24 16:59:23,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1159168. Throughput: 0: 973.2. Samples: 288424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 16:59:23,720][08483] Avg episode reward: [(0, '5.841')] | |
| [2023-02-24 16:59:23,803][14169] Saving new best policy, reward=5.841! | |
| [2023-02-24 16:59:28,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1179648. Throughput: 0: 972.9. Samples: 295144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 16:59:28,722][08483] Avg episode reward: [(0, '5.611')] | |
| [2023-02-24 16:59:30,637][14183] Updated weights for policy 0, policy_version 290 (0.0022) | |
| [2023-02-24 16:59:33,721][08483] Fps is (10 sec: 3685.0, 60 sec: 3822.8, 300 sec: 3887.7). Total num frames: 1196032. Throughput: 0: 925.0. Samples: 299450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:33,723][08483] Avg episode reward: [(0, '5.262')] | |
| [2023-02-24 16:59:38,718][08483] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3860.0). Total num frames: 1212416. Throughput: 0: 924.1. Samples: 301718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:38,724][08483] Avg episode reward: [(0, '5.127')] | |
| [2023-02-24 16:59:41,538][14183] Updated weights for policy 0, policy_version 300 (0.0019) | |
| [2023-02-24 16:59:43,717][08483] Fps is (10 sec: 4097.6, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 1236992. Throughput: 0: 974.7. Samples: 308620. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 16:59:43,725][08483] Avg episode reward: [(0, '4.904')] | |
| [2023-02-24 16:59:43,736][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000302_1236992.pth... | |
| [2023-02-24 16:59:43,837][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000075_307200.pth | |
| [2023-02-24 16:59:48,718][08483] Fps is (10 sec: 4505.3, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1257472. Throughput: 0: 954.4. Samples: 314768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 16:59:48,722][08483] Avg episode reward: [(0, '5.089')] | |
| [2023-02-24 16:59:52,520][14183] Updated weights for policy 0, policy_version 310 (0.0031) | |
| [2023-02-24 16:59:53,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3755.0, 300 sec: 3873.8). Total num frames: 1269760. Throughput: 0: 922.8. Samples: 316950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 16:59:53,720][08483] Avg episode reward: [(0, '5.295')] | |
| [2023-02-24 16:59:58,717][08483] Fps is (10 sec: 3277.0, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1290240. Throughput: 0: 923.9. Samples: 321862. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 16:59:58,723][08483] Avg episode reward: [(0, '5.698')] | |
| [2023-02-24 17:00:02,700][14183] Updated weights for policy 0, policy_version 320 (0.0029) | |
| [2023-02-24 17:00:03,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1314816. Throughput: 0: 972.4. Samples: 328924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:00:03,723][08483] Avg episode reward: [(0, '5.736')] | |
| [2023-02-24 17:00:08,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 1331200. Throughput: 0: 977.3. Samples: 332402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:00:08,723][08483] Avg episode reward: [(0, '5.934')] | |
| [2023-02-24 17:00:08,726][14169] Saving new best policy, reward=5.934! | |
| [2023-02-24 17:00:13,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3873.9). Total num frames: 1347584. Throughput: 0: 926.6. Samples: 336840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:00:13,720][08483] Avg episode reward: [(0, '5.850')] | |
| [2023-02-24 17:00:14,608][14183] Updated weights for policy 0, policy_version 330 (0.0023) | |
| [2023-02-24 17:00:18,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1368064. Throughput: 0: 947.3. Samples: 342074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:00:18,725][08483] Avg episode reward: [(0, '5.832')] | |
| [2023-02-24 17:00:23,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1388544. Throughput: 0: 969.4. Samples: 345342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:00:23,720][08483] Avg episode reward: [(0, '6.305')] | |
| [2023-02-24 17:00:23,730][14169] Saving new best policy, reward=6.305! | |
| [2023-02-24 17:00:24,279][14183] Updated weights for policy 0, policy_version 340 (0.0015) | |
| [2023-02-24 17:00:28,722][08483] Fps is (10 sec: 3684.6, 60 sec: 3754.4, 300 sec: 3859.9). Total num frames: 1404928. Throughput: 0: 955.1. Samples: 351604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:00:28,725][08483] Avg episode reward: [(0, '6.377')] | |
| [2023-02-24 17:00:28,802][14169] Saving new best policy, reward=6.377! | |
| [2023-02-24 17:00:33,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3860.0). Total num frames: 1421312. Throughput: 0: 916.1. Samples: 355994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:00:33,722][08483] Avg episode reward: [(0, '6.409')] | |
| [2023-02-24 17:00:33,735][14169] Saving new best policy, reward=6.409! | |
| [2023-02-24 17:00:36,828][14183] Updated weights for policy 0, policy_version 350 (0.0029) | |
| [2023-02-24 17:00:38,718][08483] Fps is (10 sec: 3688.1, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 1441792. Throughput: 0: 920.3. Samples: 358364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:00:38,726][08483] Avg episode reward: [(0, '5.956')] | |
| [2023-02-24 17:00:43,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 1462272. Throughput: 0: 961.8. Samples: 365142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:00:43,722][08483] Avg episode reward: [(0, '6.019')] | |
| [2023-02-24 17:00:45,918][14183] Updated weights for policy 0, policy_version 360 (0.0015) | |
| [2023-02-24 17:00:48,717][08483] Fps is (10 sec: 3686.5, 60 sec: 3686.5, 300 sec: 3846.1). Total num frames: 1478656. Throughput: 0: 928.5. Samples: 370708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:00:48,719][08483] Avg episode reward: [(0, '5.870')] | |
| [2023-02-24 17:00:53,717][08483] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 1490944. Throughput: 0: 896.2. Samples: 372730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:00:53,722][08483] Avg episode reward: [(0, '5.552')] | |
| [2023-02-24 17:00:58,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 1511424. Throughput: 0: 900.4. Samples: 377358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:00:58,720][08483] Avg episode reward: [(0, '5.733')] | |
| [2023-02-24 17:00:59,436][14183] Updated weights for policy 0, policy_version 370 (0.0013) | |
| [2023-02-24 17:01:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3818.3). Total num frames: 1531904. Throughput: 0: 928.5. Samples: 383856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:01:03,723][08483] Avg episode reward: [(0, '6.179')] | |
| [2023-02-24 17:01:08,718][08483] Fps is (10 sec: 3686.1, 60 sec: 3618.1, 300 sec: 3818.3). Total num frames: 1548288. Throughput: 0: 923.5. Samples: 386900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:01:08,726][08483] Avg episode reward: [(0, '6.301')] | |
| [2023-02-24 17:01:10,307][14183] Updated weights for policy 0, policy_version 380 (0.0018) | |
| [2023-02-24 17:01:13,719][08483] Fps is (10 sec: 3276.3, 60 sec: 3618.0, 300 sec: 3818.3). Total num frames: 1564672. Throughput: 0: 874.4. Samples: 390948. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:01:13,724][08483] Avg episode reward: [(0, '6.353')] | |
| [2023-02-24 17:01:18,717][08483] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3804.4). Total num frames: 1581056. Throughput: 0: 896.0. Samples: 396314. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:01:18,725][08483] Avg episode reward: [(0, '6.228')] | |
| [2023-02-24 17:01:21,752][14183] Updated weights for policy 0, policy_version 390 (0.0016) | |
| [2023-02-24 17:01:23,717][08483] Fps is (10 sec: 4096.6, 60 sec: 3618.1, 300 sec: 3804.4). Total num frames: 1605632. Throughput: 0: 915.1. Samples: 399544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:01:23,720][08483] Avg episode reward: [(0, '6.816')] | |
| [2023-02-24 17:01:23,729][14169] Saving new best policy, reward=6.816! | |
| [2023-02-24 17:01:28,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3618.4, 300 sec: 3804.4). Total num frames: 1622016. Throughput: 0: 901.3. Samples: 405700. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:01:28,727][08483] Avg episode reward: [(0, '6.925')] | |
| [2023-02-24 17:01:28,729][14169] Saving new best policy, reward=6.925! | |
| [2023-02-24 17:01:33,718][08483] Fps is (10 sec: 2867.0, 60 sec: 3549.8, 300 sec: 3790.5). Total num frames: 1634304. Throughput: 0: 869.8. Samples: 409852. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:01:33,721][08483] Avg episode reward: [(0, '6.894')] | |
| [2023-02-24 17:01:33,761][14183] Updated weights for policy 0, policy_version 400 (0.0019) | |
| [2023-02-24 17:01:38,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3804.5). Total num frames: 1658880. Throughput: 0: 880.7. Samples: 412360. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:01:38,720][08483] Avg episode reward: [(0, '6.635')] | |
| [2023-02-24 17:01:43,079][14183] Updated weights for policy 0, policy_version 410 (0.0021) | |
| [2023-02-24 17:01:43,717][08483] Fps is (10 sec: 4506.0, 60 sec: 3618.1, 300 sec: 3790.5). Total num frames: 1679360. Throughput: 0: 933.3. Samples: 419358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:01:43,720][08483] Avg episode reward: [(0, '7.097')] | |
| [2023-02-24 17:01:43,730][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000410_1679360.pth... | |
| [2023-02-24 17:01:43,853][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000189_774144.pth | |
| [2023-02-24 17:01:43,868][14169] Saving new best policy, reward=7.097! | |
| [2023-02-24 17:01:48,722][08483] Fps is (10 sec: 4094.1, 60 sec: 3686.1, 300 sec: 3804.4). Total num frames: 1699840. Throughput: 0: 916.9. Samples: 425120. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:01:48,725][08483] Avg episode reward: [(0, '6.560')] | |
| [2023-02-24 17:01:53,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 1712128. Throughput: 0: 896.5. Samples: 427244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:01:53,721][08483] Avg episode reward: [(0, '7.112')] | |
| [2023-02-24 17:01:53,732][14169] Saving new best policy, reward=7.112! | |
| [2023-02-24 17:01:55,977][14183] Updated weights for policy 0, policy_version 420 (0.0023) | |
| [2023-02-24 17:01:58,717][08483] Fps is (10 sec: 3278.4, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1732608. Throughput: 0: 921.9. Samples: 432430. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:01:58,723][08483] Avg episode reward: [(0, '7.203')] | |
| [2023-02-24 17:01:58,726][14169] Saving new best policy, reward=7.203! | |
| [2023-02-24 17:02:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1753088. Throughput: 0: 956.1. Samples: 439338. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:02:03,723][08483] Avg episode reward: [(0, '8.197')] | |
| [2023-02-24 17:02:03,733][14169] Saving new best policy, reward=8.197! | |
| [2023-02-24 17:02:04,917][14183] Updated weights for policy 0, policy_version 430 (0.0011) | |
| [2023-02-24 17:02:08,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 1773568. Throughput: 0: 952.0. Samples: 442384. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:02:08,724][08483] Avg episode reward: [(0, '8.153')] | |
| [2023-02-24 17:02:13,719][08483] Fps is (10 sec: 3276.3, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1785856. Throughput: 0: 913.0. Samples: 446786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:02:13,722][08483] Avg episode reward: [(0, '8.622')] | |
| [2023-02-24 17:02:13,737][14169] Saving new best policy, reward=8.622! | |
| [2023-02-24 17:02:17,158][14183] Updated weights for policy 0, policy_version 440 (0.0017) | |
| [2023-02-24 17:02:18,723][08483] Fps is (10 sec: 3275.1, 60 sec: 3754.3, 300 sec: 3762.7). Total num frames: 1806336. Throughput: 0: 948.3. Samples: 452530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:02:18,727][08483] Avg episode reward: [(0, '8.229')] | |
| [2023-02-24 17:02:23,717][08483] Fps is (10 sec: 4506.3, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1830912. Throughput: 0: 967.1. Samples: 455878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:02:23,730][08483] Avg episode reward: [(0, '8.910')] | |
| [2023-02-24 17:02:23,743][14169] Saving new best policy, reward=8.910! | |
| [2023-02-24 17:02:26,631][14183] Updated weights for policy 0, policy_version 450 (0.0028) | |
| [2023-02-24 17:02:28,717][08483] Fps is (10 sec: 4098.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1847296. Throughput: 0: 947.6. Samples: 462002. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:02:28,724][08483] Avg episode reward: [(0, '8.899')] | |
| [2023-02-24 17:02:33,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3776.7). Total num frames: 1863680. Throughput: 0: 916.1. Samples: 466340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:02:33,724][08483] Avg episode reward: [(0, '9.546')] | |
| [2023-02-24 17:02:33,738][14169] Saving new best policy, reward=9.546! | |
| [2023-02-24 17:02:38,472][14183] Updated weights for policy 0, policy_version 460 (0.0021) | |
| [2023-02-24 17:02:38,718][08483] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1884160. Throughput: 0: 927.5. Samples: 468980. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:02:38,725][08483] Avg episode reward: [(0, '9.328')] | |
| [2023-02-24 17:02:43,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1904640. Throughput: 0: 968.5. Samples: 476014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:02:43,727][08483] Avg episode reward: [(0, '9.672')] | |
| [2023-02-24 17:02:43,742][14169] Saving new best policy, reward=9.672! | |
| [2023-02-24 17:02:48,402][14183] Updated weights for policy 0, policy_version 470 (0.0011) | |
| [2023-02-24 17:02:48,720][08483] Fps is (10 sec: 4095.0, 60 sec: 3754.8, 300 sec: 3776.6). Total num frames: 1925120. Throughput: 0: 940.9. Samples: 481682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:02:48,723][08483] Avg episode reward: [(0, '9.582')] | |
| [2023-02-24 17:02:53,720][08483] Fps is (10 sec: 3275.9, 60 sec: 3754.5, 300 sec: 3762.7). Total num frames: 1937408. Throughput: 0: 919.8. Samples: 483776. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:02:53,723][08483] Avg episode reward: [(0, '9.596')] | |
| [2023-02-24 17:02:58,717][08483] Fps is (10 sec: 3277.7, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1957888. Throughput: 0: 942.7. Samples: 489204. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:02:58,726][08483] Avg episode reward: [(0, '10.036')] | |
| [2023-02-24 17:02:58,731][14169] Saving new best policy, reward=10.036! | |
| [2023-02-24 17:02:59,923][14183] Updated weights for policy 0, policy_version 480 (0.0026) | |
| [2023-02-24 17:03:03,717][08483] Fps is (10 sec: 4506.9, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1982464. Throughput: 0: 968.4. Samples: 496104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:03:03,726][08483] Avg episode reward: [(0, '10.195')] | |
| [2023-02-24 17:03:03,738][14169] Saving new best policy, reward=10.195! | |
| [2023-02-24 17:03:08,721][08483] Fps is (10 sec: 4094.4, 60 sec: 3754.4, 300 sec: 3762.8). Total num frames: 1998848. Throughput: 0: 962.5. Samples: 499192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:03:08,724][08483] Avg episode reward: [(0, '10.131')] | |
| [2023-02-24 17:03:10,618][14183] Updated weights for policy 0, policy_version 490 (0.0023) | |
| [2023-02-24 17:03:13,718][08483] Fps is (10 sec: 3276.7, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 2015232. Throughput: 0: 923.0. Samples: 503538. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:03:13,724][08483] Avg episode reward: [(0, '9.560')] | |
| [2023-02-24 17:03:18,717][08483] Fps is (10 sec: 3687.8, 60 sec: 3823.3, 300 sec: 3748.9). Total num frames: 2035712. Throughput: 0: 955.4. Samples: 509332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:03:18,724][08483] Avg episode reward: [(0, '9.297')] | |
| [2023-02-24 17:03:21,062][14183] Updated weights for policy 0, policy_version 500 (0.0022) | |
| [2023-02-24 17:03:23,717][08483] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2056192. Throughput: 0: 972.4. Samples: 512736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:03:23,721][08483] Avg episode reward: [(0, '8.310')] | |
| [2023-02-24 17:03:28,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2076672. Throughput: 0: 951.1. Samples: 518814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:03:28,724][08483] Avg episode reward: [(0, '8.456')] | |
| [2023-02-24 17:03:32,808][14183] Updated weights for policy 0, policy_version 510 (0.0026) | |
| [2023-02-24 17:03:33,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2088960. Throughput: 0: 921.7. Samples: 523156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:03:33,720][08483] Avg episode reward: [(0, '8.021')] | |
| [2023-02-24 17:03:38,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2109440. Throughput: 0: 935.3. Samples: 525860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:03:38,728][08483] Avg episode reward: [(0, '8.136')] | |
| [2023-02-24 17:03:42,537][14183] Updated weights for policy 0, policy_version 520 (0.0016) | |
| [2023-02-24 17:03:43,718][08483] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2134016. Throughput: 0: 970.3. Samples: 532868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:03:43,724][08483] Avg episode reward: [(0, '8.728')] | |
| [2023-02-24 17:03:43,736][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000521_2134016.pth... | |
| [2023-02-24 17:03:43,874][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000302_1236992.pth | |
| [2023-02-24 17:03:48,725][08483] Fps is (10 sec: 4092.8, 60 sec: 3754.4, 300 sec: 3748.9). Total num frames: 2150400. Throughput: 0: 939.2. Samples: 538376. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:03:48,728][08483] Avg episode reward: [(0, '9.599')] | |
| [2023-02-24 17:03:53,718][08483] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3748.9). Total num frames: 2166784. Throughput: 0: 917.9. Samples: 540496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:03:53,730][08483] Avg episode reward: [(0, '10.609')] | |
| [2023-02-24 17:03:53,744][14169] Saving new best policy, reward=10.609! | |
| [2023-02-24 17:03:55,328][14183] Updated weights for policy 0, policy_version 530 (0.0036) | |
| [2023-02-24 17:03:58,717][08483] Fps is (10 sec: 3279.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2183168. Throughput: 0: 929.3. Samples: 545356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:03:58,724][08483] Avg episode reward: [(0, '10.583')] | |
| [2023-02-24 17:04:03,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2203648. Throughput: 0: 945.1. Samples: 551860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:04:03,723][08483] Avg episode reward: [(0, '9.701')] | |
| [2023-02-24 17:04:04,786][14183] Updated weights for policy 0, policy_version 540 (0.0015) | |
| [2023-02-24 17:04:08,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.6, 300 sec: 3721.1). Total num frames: 2220032. Throughput: 0: 934.7. Samples: 554796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:04:08,723][08483] Avg episode reward: [(0, '9.050')] | |
| [2023-02-24 17:04:13,719][08483] Fps is (10 sec: 3276.4, 60 sec: 3686.3, 300 sec: 3721.1). Total num frames: 2236416. Throughput: 0: 897.4. Samples: 559198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:04:13,722][08483] Avg episode reward: [(0, '9.256')] | |
| [2023-02-24 17:04:17,232][14183] Updated weights for policy 0, policy_version 550 (0.0012) | |
| [2023-02-24 17:04:18,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2256896. Throughput: 0: 929.7. Samples: 564992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:04:18,723][08483] Avg episode reward: [(0, '9.311')] | |
| [2023-02-24 17:04:23,717][08483] Fps is (10 sec: 4506.1, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2281472. Throughput: 0: 942.9. Samples: 568290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:04:23,723][08483] Avg episode reward: [(0, '10.736')] | |
| [2023-02-24 17:04:23,739][14169] Saving new best policy, reward=10.736! | |
| [2023-02-24 17:04:27,193][14183] Updated weights for policy 0, policy_version 560 (0.0013) | |
| [2023-02-24 17:04:28,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2297856. Throughput: 0: 913.1. Samples: 573958. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:04:28,722][08483] Avg episode reward: [(0, '12.204')] | |
| [2023-02-24 17:04:28,724][14169] Saving new best policy, reward=12.204! | |
| [2023-02-24 17:04:33,718][08483] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2310144. Throughput: 0: 885.7. Samples: 578224. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:04:33,727][08483] Avg episode reward: [(0, '12.433')] | |
| [2023-02-24 17:04:33,740][14169] Saving new best policy, reward=12.433! | |
| [2023-02-24 17:04:38,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2330624. Throughput: 0: 900.6. Samples: 581024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:04:38,723][08483] Avg episode reward: [(0, '12.754')] | |
| [2023-02-24 17:04:38,729][14169] Saving new best policy, reward=12.754! | |
| [2023-02-24 17:04:39,370][14183] Updated weights for policy 0, policy_version 570 (0.0017) | |
| [2023-02-24 17:04:43,717][08483] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2351104. Throughput: 0: 938.5. Samples: 587588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:04:43,724][08483] Avg episode reward: [(0, '13.080')] | |
| [2023-02-24 17:04:43,735][14169] Saving new best policy, reward=13.080! | |
| [2023-02-24 17:04:48,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3618.6, 300 sec: 3721.1). Total num frames: 2367488. Throughput: 0: 911.6. Samples: 592880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:04:48,724][08483] Avg episode reward: [(0, '13.174')] | |
| [2023-02-24 17:04:48,729][14169] Saving new best policy, reward=13.174! | |
| [2023-02-24 17:04:50,686][14183] Updated weights for policy 0, policy_version 580 (0.0020) | |
| [2023-02-24 17:04:53,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2383872. Throughput: 0: 894.1. Samples: 595030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:04:53,729][08483] Avg episode reward: [(0, '13.282')] | |
| [2023-02-24 17:04:53,741][14169] Saving new best policy, reward=13.282! | |
| [2023-02-24 17:04:58,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2404352. Throughput: 0: 916.4. Samples: 600434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:04:58,723][08483] Avg episode reward: [(0, '15.086')] | |
| [2023-02-24 17:04:58,727][14169] Saving new best policy, reward=15.086! | |
| [2023-02-24 17:05:01,173][14183] Updated weights for policy 0, policy_version 590 (0.0016) | |
| [2023-02-24 17:05:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2424832. Throughput: 0: 939.5. Samples: 607270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:05:03,725][08483] Avg episode reward: [(0, '15.052')] | |
| [2023-02-24 17:05:08,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2441216. Throughput: 0: 922.9. Samples: 609820. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:08,721][08483] Avg episode reward: [(0, '15.029')] | |
| [2023-02-24 17:05:13,039][14183] Updated weights for policy 0, policy_version 600 (0.0014) | |
| [2023-02-24 17:05:13,719][08483] Fps is (10 sec: 3276.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2457600. Throughput: 0: 896.9. Samples: 614320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:13,728][08483] Avg episode reward: [(0, '15.945')] | |
| [2023-02-24 17:05:13,740][14169] Saving new best policy, reward=15.945! | |
| [2023-02-24 17:05:18,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2478080. Throughput: 0: 937.2. Samples: 620398. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:18,725][08483] Avg episode reward: [(0, '15.948')] | |
| [2023-02-24 17:05:18,729][14169] Saving new best policy, reward=15.948! | |
| [2023-02-24 17:05:22,641][14183] Updated weights for policy 0, policy_version 610 (0.0012) | |
| [2023-02-24 17:05:23,717][08483] Fps is (10 sec: 4506.2, 60 sec: 3686.4, 300 sec: 3721.2). Total num frames: 2502656. Throughput: 0: 948.4. Samples: 623700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:23,720][08483] Avg episode reward: [(0, '16.459')] | |
| [2023-02-24 17:05:23,732][14169] Saving new best policy, reward=16.459! | |
| [2023-02-24 17:05:28,727][08483] Fps is (10 sec: 3682.8, 60 sec: 3617.5, 300 sec: 3707.1). Total num frames: 2514944. Throughput: 0: 922.7. Samples: 629120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:28,730][08483] Avg episode reward: [(0, '16.520')] | |
| [2023-02-24 17:05:28,734][14169] Saving new best policy, reward=16.520! | |
| [2023-02-24 17:05:33,718][08483] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2531328. Throughput: 0: 896.4. Samples: 633220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:05:33,725][08483] Avg episode reward: [(0, '17.646')] | |
| [2023-02-24 17:05:33,739][14169] Saving new best policy, reward=17.646! | |
| [2023-02-24 17:05:35,772][14183] Updated weights for policy 0, policy_version 620 (0.0048) | |
| [2023-02-24 17:05:38,717][08483] Fps is (10 sec: 3690.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2551808. Throughput: 0: 911.3. Samples: 636040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:38,720][08483] Avg episode reward: [(0, '18.028')] | |
| [2023-02-24 17:05:38,724][14169] Saving new best policy, reward=18.028! | |
| [2023-02-24 17:05:43,718][08483] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2572288. Throughput: 0: 935.0. Samples: 642510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:05:43,721][08483] Avg episode reward: [(0, '17.543')] | |
| [2023-02-24 17:05:43,731][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000628_2572288.pth... | |
| [2023-02-24 17:05:43,853][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000410_1679360.pth | |
| [2023-02-24 17:05:45,723][14183] Updated weights for policy 0, policy_version 630 (0.0016) | |
| [2023-02-24 17:05:48,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2588672. Throughput: 0: 893.2. Samples: 647462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:05:48,720][08483] Avg episode reward: [(0, '17.698')] | |
| [2023-02-24 17:05:53,717][08483] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2600960. Throughput: 0: 882.8. Samples: 649548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:53,725][08483] Avg episode reward: [(0, '19.070')] | |
| [2023-02-24 17:05:53,742][14169] Saving new best policy, reward=19.070! | |
| [2023-02-24 17:05:57,872][14183] Updated weights for policy 0, policy_version 640 (0.0013) | |
| [2023-02-24 17:05:58,718][08483] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2621440. Throughput: 0: 909.0. Samples: 655226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:05:58,720][08483] Avg episode reward: [(0, '17.135')] | |
| [2023-02-24 17:06:03,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2646016. Throughput: 0: 934.0. Samples: 662428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:06:03,720][08483] Avg episode reward: [(0, '17.585')] | |
| [2023-02-24 17:06:07,876][14183] Updated weights for policy 0, policy_version 650 (0.0019) | |
| [2023-02-24 17:06:08,718][08483] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2662400. Throughput: 0: 916.7. Samples: 664950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:06:08,722][08483] Avg episode reward: [(0, '16.111')] | |
| [2023-02-24 17:06:13,718][08483] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2678784. Throughput: 0: 894.3. Samples: 669354. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:06:13,725][08483] Avg episode reward: [(0, '15.427')] | |
| [2023-02-24 17:06:18,670][14183] Updated weights for policy 0, policy_version 660 (0.0024) | |
| [2023-02-24 17:06:18,717][08483] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2703360. Throughput: 0: 948.1. Samples: 675882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:06:18,720][08483] Avg episode reward: [(0, '16.627')] | |
| [2023-02-24 17:06:23,718][08483] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2723840. Throughput: 0: 962.9. Samples: 679372. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:06:23,720][08483] Avg episode reward: [(0, '16.067')] | |
| [2023-02-24 17:06:28,719][08483] Fps is (10 sec: 3686.0, 60 sec: 3755.2, 300 sec: 3748.9). Total num frames: 2740224. Throughput: 0: 944.1. Samples: 684996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:06:28,722][08483] Avg episode reward: [(0, '16.694')] | |
| [2023-02-24 17:06:29,528][14183] Updated weights for policy 0, policy_version 670 (0.0011) | |
| [2023-02-24 17:06:33,717][08483] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2756608. Throughput: 0: 933.2. Samples: 689458. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:06:33,726][08483] Avg episode reward: [(0, '17.090')] | |
| [2023-02-24 17:06:38,718][08483] Fps is (10 sec: 3686.7, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2777088. Throughput: 0: 960.7. Samples: 692780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:06:38,725][08483] Avg episode reward: [(0, '16.668')] | |
| [2023-02-24 17:06:39,707][14183] Updated weights for policy 0, policy_version 680 (0.0019) | |
| [2023-02-24 17:06:43,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3735.1). Total num frames: 2801664. Throughput: 0: 993.3. Samples: 699922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:06:43,720][08483] Avg episode reward: [(0, '18.184')] | |
| [2023-02-24 17:06:48,717][08483] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2818048. Throughput: 0: 948.5. Samples: 705110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:06:48,723][08483] Avg episode reward: [(0, '17.812')] | |
| [2023-02-24 17:06:51,139][14183] Updated weights for policy 0, policy_version 690 (0.0022) | |
| [2023-02-24 17:06:53,719][08483] Fps is (10 sec: 2866.8, 60 sec: 3822.8, 300 sec: 3721.1). Total num frames: 2830336. Throughput: 0: 940.2. Samples: 707260. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:06:53,723][08483] Avg episode reward: [(0, '18.711')] | |
| [2023-02-24 17:06:58,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 2854912. Throughput: 0: 973.3. Samples: 713150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:06:58,720][08483] Avg episode reward: [(0, '18.563')] | |
| [2023-02-24 17:07:00,971][14183] Updated weights for policy 0, policy_version 700 (0.0015) | |
| [2023-02-24 17:07:03,717][08483] Fps is (10 sec: 4916.0, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 2879488. Throughput: 0: 982.4. Samples: 720092. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:03,723][08483] Avg episode reward: [(0, '18.264')] | |
| [2023-02-24 17:07:08,718][08483] Fps is (10 sec: 3686.2, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2891776. Throughput: 0: 957.8. Samples: 722472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:08,725][08483] Avg episode reward: [(0, '18.170')] | |
| [2023-02-24 17:07:13,273][14183] Updated weights for policy 0, policy_version 710 (0.0034) | |
| [2023-02-24 17:07:13,717][08483] Fps is (10 sec: 2867.2, 60 sec: 3823.0, 300 sec: 3735.1). Total num frames: 2908160. Throughput: 0: 931.3. Samples: 726904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:07:13,721][08483] Avg episode reward: [(0, '18.632')] | |
| [2023-02-24 17:07:18,717][08483] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 2932736. Throughput: 0: 973.8. Samples: 733280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:07:18,719][08483] Avg episode reward: [(0, '17.931')] | |
| [2023-02-24 17:07:22,226][14183] Updated weights for policy 0, policy_version 720 (0.0013) | |
| [2023-02-24 17:07:23,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2953216. Throughput: 0: 977.3. Samples: 736760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:07:23,725][08483] Avg episode reward: [(0, '18.549')] | |
| [2023-02-24 17:07:28,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 2969600. Throughput: 0: 941.8. Samples: 742302. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:07:28,724][08483] Avg episode reward: [(0, '19.527')] | |
| [2023-02-24 17:07:28,726][14169] Saving new best policy, reward=19.527! | |
| [2023-02-24 17:07:33,718][08483] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2981888. Throughput: 0: 923.6. Samples: 746674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:33,724][08483] Avg episode reward: [(0, '19.425')] | |
| [2023-02-24 17:07:34,755][14183] Updated weights for policy 0, policy_version 730 (0.0015) | |
| [2023-02-24 17:07:38,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3006464. Throughput: 0: 950.2. Samples: 750018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:38,721][08483] Avg episode reward: [(0, '19.353')] | |
| [2023-02-24 17:07:43,297][14183] Updated weights for policy 0, policy_version 740 (0.0012) | |
| [2023-02-24 17:07:43,718][08483] Fps is (10 sec: 4915.2, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3031040. Throughput: 0: 978.8. Samples: 757196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:43,720][08483] Avg episode reward: [(0, '18.508')] | |
| [2023-02-24 17:07:43,733][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth... | |
| [2023-02-24 17:07:43,870][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000521_2134016.pth | |
| [2023-02-24 17:07:48,718][08483] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3047424. Throughput: 0: 935.3. Samples: 762180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:07:48,725][08483] Avg episode reward: [(0, '17.586')] | |
| [2023-02-24 17:07:53,718][08483] Fps is (10 sec: 2867.2, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 3059712. Throughput: 0: 931.4. Samples: 764384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:07:53,724][08483] Avg episode reward: [(0, '17.074')] | |
| [2023-02-24 17:07:55,695][14183] Updated weights for policy 0, policy_version 750 (0.0015) | |
| [2023-02-24 17:07:58,718][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3084288. Throughput: 0: 967.4. Samples: 770438. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-24 17:07:58,724][08483] Avg episode reward: [(0, '17.332')] | |
| [2023-02-24 17:08:03,720][08483] Fps is (10 sec: 4914.2, 60 sec: 3822.8, 300 sec: 3762.8). Total num frames: 3108864. Throughput: 0: 984.2. Samples: 777572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:08:03,730][08483] Avg episode reward: [(0, '18.256')] | |
| [2023-02-24 17:08:04,821][14183] Updated weights for policy 0, policy_version 760 (0.0030) | |
| [2023-02-24 17:08:08,717][08483] Fps is (10 sec: 3686.5, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 3121152. Throughput: 0: 958.8. Samples: 779906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:08:08,723][08483] Avg episode reward: [(0, '18.214')] | |
| [2023-02-24 17:08:13,717][08483] Fps is (10 sec: 2867.8, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3137536. Throughput: 0: 937.6. Samples: 784496. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:08:13,725][08483] Avg episode reward: [(0, '18.428')] | |
| [2023-02-24 17:08:16,713][14183] Updated weights for policy 0, policy_version 770 (0.0034) | |
| [2023-02-24 17:08:18,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3162112. Throughput: 0: 985.3. Samples: 791012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:08:18,719][08483] Avg episode reward: [(0, '21.105')] | |
| [2023-02-24 17:08:18,722][14169] Saving new best policy, reward=21.105! | |
| [2023-02-24 17:08:23,717][08483] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 3186688. Throughput: 0: 989.1. Samples: 794526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:08:23,723][08483] Avg episode reward: [(0, '20.089')] | |
| [2023-02-24 17:08:26,299][14183] Updated weights for policy 0, policy_version 780 (0.0017) | |
| [2023-02-24 17:08:28,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3198976. Throughput: 0: 951.3. Samples: 800004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:08:28,724][08483] Avg episode reward: [(0, '19.439')] | |
| [2023-02-24 17:08:33,717][08483] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3215360. Throughput: 0: 940.5. Samples: 804500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:08:33,723][08483] Avg episode reward: [(0, '18.912')] | |
| [2023-02-24 17:08:37,503][14183] Updated weights for policy 0, policy_version 790 (0.0019) | |
| [2023-02-24 17:08:38,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3239936. Throughput: 0: 967.9. Samples: 807938. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:08:38,724][08483] Avg episode reward: [(0, '18.558')] | |
| [2023-02-24 17:08:43,718][08483] Fps is (10 sec: 4915.0, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 3264512. Throughput: 0: 994.2. Samples: 815178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:08:43,720][08483] Avg episode reward: [(0, '18.344')] | |
| [2023-02-24 17:08:47,964][14183] Updated weights for policy 0, policy_version 800 (0.0017) | |
| [2023-02-24 17:08:48,718][08483] Fps is (10 sec: 3686.1, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3276800. Throughput: 0: 941.7. Samples: 819948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:08:48,721][08483] Avg episode reward: [(0, '18.667')] | |
| [2023-02-24 17:08:53,717][08483] Fps is (10 sec: 2457.7, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 3289088. Throughput: 0: 935.3. Samples: 821994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:08:53,722][08483] Avg episode reward: [(0, '19.666')] | |
| [2023-02-24 17:08:58,717][08483] Fps is (10 sec: 3686.7, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 3313664. Throughput: 0: 961.2. Samples: 827752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:08:58,720][08483] Avg episode reward: [(0, '21.437')] | |
| [2023-02-24 17:08:58,723][14169] Saving new best policy, reward=21.437! | |
| [2023-02-24 17:08:59,449][14183] Updated weights for policy 0, policy_version 810 (0.0015) | |
| [2023-02-24 17:09:03,718][08483] Fps is (10 sec: 4915.0, 60 sec: 3823.1, 300 sec: 3790.5). Total num frames: 3338240. Throughput: 0: 971.5. Samples: 834728. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:09:03,725][08483] Avg episode reward: [(0, '21.409')] | |
| [2023-02-24 17:09:08,720][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3350528. Throughput: 0: 946.0. Samples: 837094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:09:08,722][08483] Avg episode reward: [(0, '22.851')] | |
| [2023-02-24 17:09:08,726][14169] Saving new best policy, reward=22.851! | |
| [2023-02-24 17:09:10,680][14183] Updated weights for policy 0, policy_version 820 (0.0015) | |
| [2023-02-24 17:09:13,717][08483] Fps is (10 sec: 2867.3, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3366912. Throughput: 0: 921.9. Samples: 841490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:09:13,724][08483] Avg episode reward: [(0, '23.495')] | |
| [2023-02-24 17:09:13,736][14169] Saving new best policy, reward=23.495! | |
| [2023-02-24 17:09:18,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3391488. Throughput: 0: 967.6. Samples: 848040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:09:18,725][08483] Avg episode reward: [(0, '20.987')] | |
| [2023-02-24 17:09:20,475][14183] Updated weights for policy 0, policy_version 830 (0.0031) | |
| [2023-02-24 17:09:23,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 3411968. Throughput: 0: 969.1. Samples: 851546. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:09:23,727][08483] Avg episode reward: [(0, '20.516')] | |
| [2023-02-24 17:09:28,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3428352. Throughput: 0: 927.9. Samples: 856932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:09:28,720][08483] Avg episode reward: [(0, '20.948')] | |
| [2023-02-24 17:09:32,513][14183] Updated weights for policy 0, policy_version 840 (0.0014) | |
| [2023-02-24 17:09:33,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3444736. Throughput: 0: 920.5. Samples: 861370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:09:33,720][08483] Avg episode reward: [(0, '21.190')] | |
| [2023-02-24 17:09:38,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3465216. Throughput: 0: 955.1. Samples: 864972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:09:38,719][08483] Avg episode reward: [(0, '20.088')] | |
| [2023-02-24 17:09:41,392][14183] Updated weights for policy 0, policy_version 850 (0.0025) | |
| [2023-02-24 17:09:43,719][08483] Fps is (10 sec: 4504.8, 60 sec: 3754.6, 300 sec: 3804.4). Total num frames: 3489792. Throughput: 0: 984.1. Samples: 872036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:09:43,727][08483] Avg episode reward: [(0, '21.881')] | |
| [2023-02-24 17:09:43,746][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000852_3489792.pth... | |
| [2023-02-24 17:09:43,872][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000628_2572288.pth | |
| [2023-02-24 17:09:48,718][08483] Fps is (10 sec: 4095.7, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3506176. Throughput: 0: 938.2. Samples: 876948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:09:48,722][08483] Avg episode reward: [(0, '21.465')] | |
| [2023-02-24 17:09:53,601][14183] Updated weights for policy 0, policy_version 860 (0.0021) | |
| [2023-02-24 17:09:53,717][08483] Fps is (10 sec: 3277.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3522560. Throughput: 0: 935.1. Samples: 879174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:09:53,727][08483] Avg episode reward: [(0, '20.801')] | |
| [2023-02-24 17:09:58,717][08483] Fps is (10 sec: 3686.7, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3543040. Throughput: 0: 979.2. Samples: 885556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:09:58,725][08483] Avg episode reward: [(0, '20.269')] | |
| [2023-02-24 17:10:02,299][14183] Updated weights for policy 0, policy_version 870 (0.0042) | |
| [2023-02-24 17:10:03,719][08483] Fps is (10 sec: 4504.7, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 3567616. Throughput: 0: 985.3. Samples: 892380. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:10:03,725][08483] Avg episode reward: [(0, '19.642')] | |
| [2023-02-24 17:10:08,724][08483] Fps is (10 sec: 3683.9, 60 sec: 3822.5, 300 sec: 3804.4). Total num frames: 3579904. Throughput: 0: 957.5. Samples: 894642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:10:08,738][08483] Avg episode reward: [(0, '19.154')] | |
| [2023-02-24 17:10:13,717][08483] Fps is (10 sec: 2867.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3596288. Throughput: 0: 937.5. Samples: 899118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:10:13,720][08483] Avg episode reward: [(0, '19.540')] | |
| [2023-02-24 17:10:14,598][14183] Updated weights for policy 0, policy_version 880 (0.0015) | |
| [2023-02-24 17:10:18,717][08483] Fps is (10 sec: 4098.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3620864. Throughput: 0: 993.9. Samples: 906096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:10:18,729][08483] Avg episode reward: [(0, '20.070')] | |
| [2023-02-24 17:10:23,399][14183] Updated weights for policy 0, policy_version 890 (0.0019) | |
| [2023-02-24 17:10:23,717][08483] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3832.3). Total num frames: 3645440. Throughput: 0: 993.7. Samples: 909690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:10:23,721][08483] Avg episode reward: [(0, '20.475')] | |
| [2023-02-24 17:10:28,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3657728. Throughput: 0: 950.6. Samples: 914810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:10:28,724][08483] Avg episode reward: [(0, '20.191')] | |
| [2023-02-24 17:10:33,717][08483] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3674112. Throughput: 0: 947.8. Samples: 919600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:10:33,720][08483] Avg episode reward: [(0, '18.666')] | |
| [2023-02-24 17:10:35,554][14183] Updated weights for policy 0, policy_version 900 (0.0025) | |
| [2023-02-24 17:10:38,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3698688. Throughput: 0: 979.0. Samples: 923230. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-24 17:10:38,720][08483] Avg episode reward: [(0, '18.868')] | |
| [2023-02-24 17:10:43,717][08483] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 3719168. Throughput: 0: 998.4. Samples: 930486. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-24 17:10:43,724][08483] Avg episode reward: [(0, '20.125')] | |
| [2023-02-24 17:10:44,933][14183] Updated weights for policy 0, policy_version 910 (0.0025) | |
| [2023-02-24 17:10:48,723][08483] Fps is (10 sec: 3684.3, 60 sec: 3822.6, 300 sec: 3846.0). Total num frames: 3735552. Throughput: 0: 946.1. Samples: 934958. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:10:48,732][08483] Avg episode reward: [(0, '19.810')] | |
| [2023-02-24 17:10:53,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 3756032. Throughput: 0: 946.8. Samples: 937240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:10:53,721][08483] Avg episode reward: [(0, '20.833')] | |
| [2023-02-24 17:10:56,095][14183] Updated weights for policy 0, policy_version 920 (0.0015) | |
| [2023-02-24 17:10:58,717][08483] Fps is (10 sec: 4508.2, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 3780608. Throughput: 0: 999.6. Samples: 944102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:10:58,720][08483] Avg episode reward: [(0, '22.768')] | |
| [2023-02-24 17:11:03,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3846.1). Total num frames: 3796992. Throughput: 0: 987.2. Samples: 950518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:03,720][08483] Avg episode reward: [(0, '22.508')] | |
| [2023-02-24 17:11:06,424][14183] Updated weights for policy 0, policy_version 930 (0.0019) | |
| [2023-02-24 17:11:08,717][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.6, 300 sec: 3846.1). Total num frames: 3813376. Throughput: 0: 957.2. Samples: 952764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:08,720][08483] Avg episode reward: [(0, '22.935')] | |
| [2023-02-24 17:11:13,721][08483] Fps is (10 sec: 3275.6, 60 sec: 3891.0, 300 sec: 3818.3). Total num frames: 3829760. Throughput: 0: 948.7. Samples: 957504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:13,724][08483] Avg episode reward: [(0, '23.340')] | |
| [2023-02-24 17:11:17,104][14183] Updated weights for policy 0, policy_version 940 (0.0012) | |
| [2023-02-24 17:11:18,717][08483] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3854336. Throughput: 0: 1001.2. Samples: 964656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:18,720][08483] Avg episode reward: [(0, '21.961')] | |
| [2023-02-24 17:11:23,718][08483] Fps is (10 sec: 4916.9, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 3878912. Throughput: 0: 1001.7. Samples: 968306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:23,722][08483] Avg episode reward: [(0, '21.468')] | |
| [2023-02-24 17:11:27,665][14183] Updated weights for policy 0, policy_version 950 (0.0022) | |
| [2023-02-24 17:11:28,717][08483] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 3891200. Throughput: 0: 946.8. Samples: 973090. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:28,724][08483] Avg episode reward: [(0, '20.796')] | |
| [2023-02-24 17:11:33,717][08483] Fps is (10 sec: 3276.9, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 3911680. Throughput: 0: 962.3. Samples: 978258. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-24 17:11:33,725][08483] Avg episode reward: [(0, '21.452')] | |
| [2023-02-24 17:11:37,828][14183] Updated weights for policy 0, policy_version 960 (0.0021) | |
| [2023-02-24 17:11:38,718][08483] Fps is (10 sec: 4505.4, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 3936256. Throughput: 0: 988.8. Samples: 981736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:38,720][08483] Avg episode reward: [(0, '21.569')] | |
| [2023-02-24 17:11:43,719][08483] Fps is (10 sec: 4505.1, 60 sec: 3959.4, 300 sec: 3859.9). Total num frames: 3956736. Throughput: 0: 991.4. Samples: 988714. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-24 17:11:43,729][08483] Avg episode reward: [(0, '22.637')] | |
| [2023-02-24 17:11:43,747][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000966_3956736.pth... | |
| [2023-02-24 17:11:43,912][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000740_3031040.pth | |
| [2023-02-24 17:11:48,718][08483] Fps is (10 sec: 3276.8, 60 sec: 3891.6, 300 sec: 3860.0). Total num frames: 3969024. Throughput: 0: 949.7. Samples: 993254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-24 17:11:48,724][08483] Avg episode reward: [(0, '22.261')] | |
| [2023-02-24 17:11:49,000][14183] Updated weights for policy 0, policy_version 970 (0.0023) | |
| [2023-02-24 17:11:53,717][08483] Fps is (10 sec: 3277.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 3989504. Throughput: 0: 953.0. Samples: 995648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-24 17:11:53,719][08483] Avg episode reward: [(0, '22.587')] | |
| [2023-02-24 17:11:56,521][14169] Stopping Batcher_0... | |
| [2023-02-24 17:11:56,522][08483] Component Batcher_0 stopped! | |
| [2023-02-24 17:11:56,522][14169] Loop batcher_evt_loop terminating... | |
| [2023-02-24 17:11:56,523][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:11:56,571][08483] Component RolloutWorker_w5 stopped! | |
| [2023-02-24 17:11:56,578][14188] Stopping RolloutWorker_w5... | |
| [2023-02-24 17:11:56,583][14188] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-24 17:11:56,590][08483] Component RolloutWorker_w1 stopped! | |
| [2023-02-24 17:11:56,597][08483] Component RolloutWorker_w2 stopped! | |
| [2023-02-24 17:11:56,586][14183] Weights refcount: 2 0 | |
| [2023-02-24 17:11:56,603][14185] Stopping RolloutWorker_w1... | |
| [2023-02-24 17:11:56,600][14190] Stopping RolloutWorker_w6... | |
| [2023-02-24 17:11:56,603][08483] Component RolloutWorker_w6 stopped! | |
| [2023-02-24 17:11:56,596][14186] Stopping RolloutWorker_w2... | |
| [2023-02-24 17:11:56,612][08483] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-24 17:11:56,611][14183] Stopping InferenceWorker_p0-w0... | |
| [2023-02-24 17:11:56,614][14183] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-24 17:11:56,621][08483] Component RolloutWorker_w3 stopped! | |
| [2023-02-24 17:11:56,607][14190] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-24 17:11:56,622][14189] Stopping RolloutWorker_w3... | |
| [2023-02-24 17:11:56,629][14189] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-24 17:11:56,604][14185] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-24 17:11:56,613][14186] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-24 17:11:56,640][14187] Stopping RolloutWorker_w4... | |
| [2023-02-24 17:11:56,638][08483] Component RolloutWorker_w7 stopped! | |
| [2023-02-24 17:11:56,643][08483] Component RolloutWorker_w0 stopped! | |
| [2023-02-24 17:11:56,639][14184] Stopping RolloutWorker_w0... | |
| [2023-02-24 17:11:56,648][08483] Component RolloutWorker_w4 stopped! | |
| [2023-02-24 17:11:56,652][14191] Stopping RolloutWorker_w7... | |
| [2023-02-24 17:11:56,653][14191] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-24 17:11:56,641][14187] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-24 17:11:56,649][14184] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-24 17:11:56,789][14169] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000852_3489792.pth | |
| [2023-02-24 17:11:56,810][14169] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:11:57,017][08483] Component LearnerWorker_p0 stopped! | |
| [2023-02-24 17:11:57,025][08483] Waiting for process learner_proc0 to stop... | |
| [2023-02-24 17:11:57,027][14169] Stopping LearnerWorker_p0... | |
| [2023-02-24 17:11:57,028][14169] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-24 17:11:58,801][08483] Waiting for process inference_proc0-0 to join... | |
| [2023-02-24 17:11:59,255][08483] Waiting for process rollout_proc0 to join... | |
| [2023-02-24 17:11:59,268][08483] Waiting for process rollout_proc1 to join... | |
| [2023-02-24 17:11:59,439][08483] Waiting for process rollout_proc2 to join... | |
| [2023-02-24 17:11:59,441][08483] Waiting for process rollout_proc3 to join... | |
| [2023-02-24 17:11:59,445][08483] Waiting for process rollout_proc4 to join... | |
| [2023-02-24 17:11:59,448][08483] Waiting for process rollout_proc5 to join... | |
| [2023-02-24 17:11:59,452][08483] Waiting for process rollout_proc6 to join... | |
| [2023-02-24 17:11:59,453][08483] Waiting for process rollout_proc7 to join... | |
| [2023-02-24 17:11:59,455][08483] Batcher 0 profile tree view: | |
| batching: 24.8312, releasing_batches: 0.0267 | |
| [2023-02-24 17:11:59,460][08483] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 523.5232 | |
| update_model: 7.7328 | |
| weight_update: 0.0031 | |
| one_step: 0.0033 | |
| handle_policy_step: 495.3495 | |
| deserialize: 14.4760, stack: 2.8553, obs_to_device_normalize: 111.9192, forward: 236.3426, send_messages: 25.7309 | |
| prepare_outputs: 79.4053 | |
| to_cpu: 49.6594 | |
| [2023-02-24 17:11:59,463][08483] Learner 0 profile tree view: | |
| misc: 0.0054, prepare_batch: 15.4975 | |
| train: 75.1876 | |
| epoch_init: 0.0062, minibatch_init: 0.0076, losses_postprocess: 0.6879, kl_divergence: 0.5660, after_optimizer: 32.9197 | |
| calculate_losses: 26.2863 | |
| losses_init: 0.0063, forward_head: 1.5964, bptt_initial: 17.5962, tail: 1.0269, advantages_returns: 0.2892, losses: 3.2239 | |
| bptt: 2.2591 | |
| bptt_forward_core: 2.1897 | |
| update: 14.0563 | |
| clip: 1.4378 | |
| [2023-02-24 17:11:59,471][08483] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3915, enqueue_policy_requests: 138.7499, env_step: 802.5450, overhead: 19.6370, complete_rollouts: 7.1784 | |
| save_policy_outputs: 18.9521 | |
| split_output_tensors: 9.0352 | |
| [2023-02-24 17:11:59,476][08483] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.2704, enqueue_policy_requests: 145.1968, env_step: 797.5569, overhead: 19.5780, complete_rollouts: 6.2625 | |
| save_policy_outputs: 19.8273 | |
| split_output_tensors: 9.9539 | |
| [2023-02-24 17:11:59,478][08483] Loop Runner_EvtLoop terminating... | |
| [2023-02-24 17:11:59,480][08483] Runner profile tree view: | |
| main_loop: 1090.7229 | |
| [2023-02-24 17:11:59,481][08483] Collected {0: 4005888}, FPS: 3672.7 | |
| [2023-02-24 17:16:54,548][08483] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-24 17:16:54,550][08483] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-24 17:16:54,553][08483] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-24 17:16:54,555][08483] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-24 17:16:54,557][08483] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-24 17:16:54,560][08483] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-24 17:16:54,562][08483] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-24 17:16:54,565][08483] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-24 17:16:54,566][08483] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-24 17:16:54,567][08483] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-24 17:16:54,574][08483] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-24 17:16:54,575][08483] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-24 17:16:54,576][08483] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-24 17:16:54,578][08483] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-24 17:16:54,579][08483] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-24 17:16:54,605][08483] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-24 17:16:54,608][08483] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:16:54,610][08483] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:16:54,629][08483] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:16:55,327][08483] Conv encoder output size: 512 | |
| [2023-02-24 17:16:55,329][08483] Policy head output size: 512 | |
| [2023-02-24 17:16:57,693][08483] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:16:59,173][08483] Num frames 100... | |
| [2023-02-24 17:16:59,355][08483] Num frames 200... | |
| [2023-02-24 17:16:59,526][08483] Num frames 300... | |
| [2023-02-24 17:16:59,699][08483] Num frames 400... | |
| [2023-02-24 17:16:59,857][08483] Num frames 500... | |
| [2023-02-24 17:17:00,012][08483] Num frames 600... | |
| [2023-02-24 17:17:00,166][08483] Num frames 700... | |
| [2023-02-24 17:17:00,323][08483] Num frames 800... | |
| [2023-02-24 17:17:00,483][08483] Num frames 900... | |
| [2023-02-24 17:17:00,587][08483] Avg episode rewards: #0: 18.280, true rewards: #0: 9.280 | |
| [2023-02-24 17:17:00,589][08483] Avg episode reward: 18.280, avg true_objective: 9.280 | |
| [2023-02-24 17:17:00,714][08483] Num frames 1000... | |
| [2023-02-24 17:17:00,871][08483] Num frames 1100... | |
| [2023-02-24 17:17:01,027][08483] Num frames 1200... | |
| [2023-02-24 17:17:01,186][08483] Num frames 1300... | |
| [2023-02-24 17:17:01,341][08483] Num frames 1400... | |
| [2023-02-24 17:17:01,509][08483] Num frames 1500... | |
| [2023-02-24 17:17:01,674][08483] Num frames 1600... | |
| [2023-02-24 17:17:01,834][08483] Num frames 1700... | |
| [2023-02-24 17:17:01,955][08483] Num frames 1800... | |
| [2023-02-24 17:17:02,071][08483] Num frames 1900... | |
| [2023-02-24 17:17:02,182][08483] Num frames 2000... | |
| [2023-02-24 17:17:02,298][08483] Num frames 2100... | |
| [2023-02-24 17:17:02,410][08483] Num frames 2200... | |
| [2023-02-24 17:17:02,525][08483] Num frames 2300... | |
| [2023-02-24 17:17:02,638][08483] Num frames 2400... | |
| [2023-02-24 17:17:02,738][08483] Avg episode rewards: #0: 26.160, true rewards: #0: 12.160 | |
| [2023-02-24 17:17:02,740][08483] Avg episode reward: 26.160, avg true_objective: 12.160 | |
| [2023-02-24 17:17:02,817][08483] Num frames 2500... | |
| [2023-02-24 17:17:02,930][08483] Num frames 2600... | |
| [2023-02-24 17:17:03,042][08483] Num frames 2700... | |
| [2023-02-24 17:17:03,158][08483] Num frames 2800... | |
| [2023-02-24 17:17:03,270][08483] Num frames 2900... | |
| [2023-02-24 17:17:03,382][08483] Num frames 3000... | |
| [2023-02-24 17:17:03,495][08483] Num frames 3100... | |
| [2023-02-24 17:17:03,610][08483] Num frames 3200... | |
| [2023-02-24 17:17:03,726][08483] Num frames 3300... | |
| [2023-02-24 17:17:03,838][08483] Num frames 3400... | |
| [2023-02-24 17:17:03,956][08483] Avg episode rewards: #0: 25.187, true rewards: #0: 11.520 | |
| [2023-02-24 17:17:03,958][08483] Avg episode reward: 25.187, avg true_objective: 11.520 | |
| [2023-02-24 17:17:04,009][08483] Num frames 3500... | |
| [2023-02-24 17:17:04,118][08483] Num frames 3600... | |
| [2023-02-24 17:17:04,227][08483] Num frames 3700... | |
| [2023-02-24 17:17:04,344][08483] Num frames 3800... | |
| [2023-02-24 17:17:04,464][08483] Num frames 3900... | |
| [2023-02-24 17:17:04,574][08483] Num frames 4000... | |
| [2023-02-24 17:17:04,692][08483] Num frames 4100... | |
| [2023-02-24 17:17:04,820][08483] Num frames 4200... | |
| [2023-02-24 17:17:04,932][08483] Num frames 4300... | |
| [2023-02-24 17:17:05,043][08483] Num frames 4400... | |
| [2023-02-24 17:17:05,158][08483] Num frames 4500... | |
| [2023-02-24 17:17:05,277][08483] Num frames 4600... | |
| [2023-02-24 17:17:05,401][08483] Num frames 4700... | |
| [2023-02-24 17:17:05,522][08483] Num frames 4800... | |
| [2023-02-24 17:17:05,637][08483] Num frames 4900... | |
| [2023-02-24 17:17:05,764][08483] Num frames 5000... | |
| [2023-02-24 17:17:05,895][08483] Num frames 5100... | |
| [2023-02-24 17:17:06,021][08483] Num frames 5200... | |
| [2023-02-24 17:17:06,144][08483] Num frames 5300... | |
| [2023-02-24 17:17:06,271][08483] Num frames 5400... | |
| [2023-02-24 17:17:06,396][08483] Num frames 5500... | |
| [2023-02-24 17:17:06,518][08483] Avg episode rewards: #0: 32.890, true rewards: #0: 13.890 | |
| [2023-02-24 17:17:06,520][08483] Avg episode reward: 32.890, avg true_objective: 13.890 | |
| [2023-02-24 17:17:06,575][08483] Num frames 5600... | |
| [2023-02-24 17:17:06,707][08483] Num frames 5700... | |
| [2023-02-24 17:17:06,828][08483] Num frames 5800... | |
| [2023-02-24 17:17:06,942][08483] Num frames 5900... | |
| [2023-02-24 17:17:07,056][08483] Num frames 6000... | |
| [2023-02-24 17:17:07,170][08483] Num frames 6100... | |
| [2023-02-24 17:17:07,286][08483] Num frames 6200... | |
| [2023-02-24 17:17:07,414][08483] Num frames 6300... | |
| [2023-02-24 17:17:07,531][08483] Num frames 6400... | |
| [2023-02-24 17:17:07,647][08483] Num frames 6500... | |
| [2023-02-24 17:17:07,761][08483] Num frames 6600... | |
| [2023-02-24 17:17:07,898][08483] Num frames 6700... | |
| [2023-02-24 17:17:08,022][08483] Num frames 6800... | |
| [2023-02-24 17:17:08,149][08483] Num frames 6900... | |
| [2023-02-24 17:17:08,282][08483] Num frames 7000... | |
| [2023-02-24 17:17:08,408][08483] Num frames 7100... | |
| [2023-02-24 17:17:08,525][08483] Num frames 7200... | |
| [2023-02-24 17:17:08,643][08483] Num frames 7300... | |
| [2023-02-24 17:17:08,761][08483] Num frames 7400... | |
| [2023-02-24 17:17:08,881][08483] Num frames 7500... | |
| [2023-02-24 17:17:08,993][08483] Num frames 7600... | |
| [2023-02-24 17:17:09,111][08483] Avg episode rewards: #0: 37.312, true rewards: #0: 15.312 | |
| [2023-02-24 17:17:09,113][08483] Avg episode reward: 37.312, avg true_objective: 15.312 | |
| [2023-02-24 17:17:09,164][08483] Num frames 7700... | |
| [2023-02-24 17:17:09,280][08483] Num frames 7800... | |
| [2023-02-24 17:17:09,392][08483] Num frames 7900... | |
| [2023-02-24 17:17:09,501][08483] Num frames 8000... | |
| [2023-02-24 17:17:09,611][08483] Num frames 8100... | |
| [2023-02-24 17:17:09,720][08483] Num frames 8200... | |
| [2023-02-24 17:17:09,836][08483] Num frames 8300... | |
| [2023-02-24 17:17:09,954][08483] Num frames 8400... | |
| [2023-02-24 17:17:10,064][08483] Num frames 8500... | |
| [2023-02-24 17:17:10,209][08483] Avg episode rewards: #0: 33.973, true rewards: #0: 14.307 | |
| [2023-02-24 17:17:10,210][08483] Avg episode reward: 33.973, avg true_objective: 14.307 | |
| [2023-02-24 17:17:10,232][08483] Num frames 8600... | |
| [2023-02-24 17:17:10,347][08483] Num frames 8700... | |
| [2023-02-24 17:17:10,459][08483] Num frames 8800... | |
| [2023-02-24 17:17:10,571][08483] Num frames 8900... | |
| [2023-02-24 17:17:10,685][08483] Num frames 9000... | |
| [2023-02-24 17:17:10,800][08483] Num frames 9100... | |
| [2023-02-24 17:17:10,921][08483] Num frames 9200... | |
| [2023-02-24 17:17:11,070][08483] Avg episode rewards: #0: 30.697, true rewards: #0: 13.269 | |
| [2023-02-24 17:17:11,072][08483] Avg episode reward: 30.697, avg true_objective: 13.269 | |
| [2023-02-24 17:17:11,089][08483] Num frames 9300... | |
| [2023-02-24 17:17:11,196][08483] Num frames 9400... | |
| [2023-02-24 17:17:11,304][08483] Num frames 9500... | |
| [2023-02-24 17:17:11,416][08483] Num frames 9600... | |
| [2023-02-24 17:17:11,525][08483] Num frames 9700... | |
| [2023-02-24 17:17:11,633][08483] Num frames 9800... | |
| [2023-02-24 17:17:11,756][08483] Avg episode rewards: #0: 28.080, true rewards: #0: 12.330 | |
| [2023-02-24 17:17:11,757][08483] Avg episode reward: 28.080, avg true_objective: 12.330 | |
| [2023-02-24 17:17:11,802][08483] Num frames 9900... | |
| [2023-02-24 17:17:11,942][08483] Num frames 10000... | |
| [2023-02-24 17:17:12,094][08483] Num frames 10100... | |
| [2023-02-24 17:17:12,252][08483] Num frames 10200... | |
| [2023-02-24 17:17:12,407][08483] Num frames 10300... | |
| [2023-02-24 17:17:12,566][08483] Num frames 10400... | |
| [2023-02-24 17:17:12,720][08483] Num frames 10500... | |
| [2023-02-24 17:17:12,881][08483] Num frames 10600... | |
| [2023-02-24 17:17:13,039][08483] Num frames 10700... | |
| [2023-02-24 17:17:13,197][08483] Num frames 10800... | |
| [2023-02-24 17:17:13,352][08483] Num frames 10900... | |
| [2023-02-24 17:17:13,508][08483] Num frames 11000... | |
| [2023-02-24 17:17:13,637][08483] Avg episode rewards: #0: 28.053, true rewards: #0: 12.276 | |
| [2023-02-24 17:17:13,638][08483] Avg episode reward: 28.053, avg true_objective: 12.276 | |
| [2023-02-24 17:17:13,724][08483] Num frames 11100... | |
| [2023-02-24 17:17:13,883][08483] Num frames 11200... | |
| [2023-02-24 17:17:14,044][08483] Num frames 11300... | |
| [2023-02-24 17:17:14,205][08483] Num frames 11400... | |
| [2023-02-24 17:17:14,368][08483] Num frames 11500... | |
| [2023-02-24 17:17:14,532][08483] Num frames 11600... | |
| [2023-02-24 17:17:14,695][08483] Num frames 11700... | |
| [2023-02-24 17:17:14,861][08483] Num frames 11800... | |
| [2023-02-24 17:17:15,026][08483] Num frames 11900... | |
| [2023-02-24 17:17:15,186][08483] Num frames 12000... | |
| [2023-02-24 17:17:15,360][08483] Num frames 12100... | |
| [2023-02-24 17:17:15,473][08483] Num frames 12200... | |
| [2023-02-24 17:17:15,589][08483] Num frames 12300... | |
| [2023-02-24 17:17:15,702][08483] Num frames 12400... | |
| [2023-02-24 17:17:15,816][08483] Num frames 12500... | |
| [2023-02-24 17:17:15,932][08483] Num frames 12600... | |
| [2023-02-24 17:17:16,048][08483] Num frames 12700... | |
| [2023-02-24 17:17:16,159][08483] Num frames 12800... | |
| [2023-02-24 17:17:16,272][08483] Num frames 12900... | |
| [2023-02-24 17:17:16,390][08483] Num frames 13000... | |
| [2023-02-24 17:17:16,504][08483] Num frames 13100... | |
| [2023-02-24 17:17:16,614][08483] Avg episode rewards: #0: 30.648, true rewards: #0: 13.148 | |
| [2023-02-24 17:17:16,615][08483] Avg episode reward: 30.648, avg true_objective: 13.148 | |
| [2023-02-24 17:18:34,198][08483] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-24 17:24:55,238][08483] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-24 17:24:55,240][08483] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-24 17:24:55,242][08483] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-24 17:24:55,244][08483] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-24 17:24:55,245][08483] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-24 17:24:55,249][08483] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-24 17:24:55,252][08483] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-24 17:24:55,254][08483] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-24 17:24:55,256][08483] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-24 17:24:55,257][08483] Adding new argument 'hf_repository'='robotman0/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-24 17:24:55,258][08483] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-24 17:24:55,259][08483] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-24 17:24:55,260][08483] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-24 17:24:55,261][08483] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-24 17:24:55,262][08483] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-24 17:24:55,287][08483] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-24 17:24:55,289][08483] RunningMeanStd input shape: (1,) | |
| [2023-02-24 17:24:55,304][08483] ConvEncoder: input_channels=3 | |
| [2023-02-24 17:24:55,341][08483] Conv encoder output size: 512 | |
| [2023-02-24 17:24:55,344][08483] Policy head output size: 512 | |
| [2023-02-24 17:24:55,364][08483] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-24 17:24:55,795][08483] Num frames 100... | |
| [2023-02-24 17:24:55,905][08483] Num frames 200... | |
| [2023-02-24 17:24:56,018][08483] Num frames 300... | |
| [2023-02-24 17:24:56,134][08483] Num frames 400... | |
| [2023-02-24 17:24:56,245][08483] Num frames 500... | |
| [2023-02-24 17:24:56,364][08483] Num frames 600... | |
| [2023-02-24 17:24:56,481][08483] Num frames 700... | |
| [2023-02-24 17:24:56,614][08483] Avg episode rewards: #0: 16.670, true rewards: #0: 7.670 | |
| [2023-02-24 17:24:56,616][08483] Avg episode reward: 16.670, avg true_objective: 7.670 | |
| [2023-02-24 17:24:56,655][08483] Num frames 800... | |
| [2023-02-24 17:24:56,766][08483] Num frames 900... | |
| [2023-02-24 17:24:56,876][08483] Num frames 1000... | |
| [2023-02-24 17:24:56,987][08483] Num frames 1100... | |
| [2023-02-24 17:24:57,104][08483] Num frames 1200... | |
| [2023-02-24 17:24:57,220][08483] Num frames 1300... | |
| [2023-02-24 17:24:57,333][08483] Num frames 1400... | |
| [2023-02-24 17:24:57,464][08483] Num frames 1500... | |
| [2023-02-24 17:24:57,576][08483] Num frames 1600... | |
| [2023-02-24 17:24:57,667][08483] Avg episode rewards: #0: 17.155, true rewards: #0: 8.155 | |
| [2023-02-24 17:24:57,669][08483] Avg episode reward: 17.155, avg true_objective: 8.155 | |
| [2023-02-24 17:24:57,755][08483] Num frames 1700... | |
| [2023-02-24 17:24:57,865][08483] Num frames 1800... | |
| [2023-02-24 17:24:57,975][08483] Num frames 1900... | |
| [2023-02-24 17:24:58,089][08483] Num frames 2000... | |
| [2023-02-24 17:24:58,206][08483] Num frames 2100... | |
| [2023-02-24 17:24:58,319][08483] Num frames 2200... | |
| [2023-02-24 17:24:58,435][08483] Num frames 2300... | |
| [2023-02-24 17:24:58,546][08483] Num frames 2400... | |
| [2023-02-24 17:24:58,659][08483] Num frames 2500... | |
| [2023-02-24 17:24:58,771][08483] Num frames 2600... | |
| [2023-02-24 17:24:58,885][08483] Num frames 2700... | |
| [2023-02-24 17:24:58,996][08483] Num frames 2800... | |
| [2023-02-24 17:24:59,111][08483] Num frames 2900... | |
| [2023-02-24 17:24:59,229][08483] Num frames 3000... | |
| [2023-02-24 17:24:59,345][08483] Num frames 3100... | |
| [2023-02-24 17:24:59,407][08483] Avg episode rewards: #0: 21.010, true rewards: #0: 10.343 | |
| [2023-02-24 17:24:59,410][08483] Avg episode reward: 21.010, avg true_objective: 10.343 | |
| [2023-02-24 17:24:59,518][08483] Num frames 3200... | |
| [2023-02-24 17:24:59,629][08483] Num frames 3300... | |
| [2023-02-24 17:24:59,744][08483] Num frames 3400... | |
| [2023-02-24 17:24:59,855][08483] Num frames 3500... | |
| [2023-02-24 17:24:59,969][08483] Num frames 3600... | |
| [2023-02-24 17:25:00,079][08483] Num frames 3700... | |
| [2023-02-24 17:25:00,196][08483] Num frames 3800... | |
| [2023-02-24 17:25:00,306][08483] Num frames 3900... | |
| [2023-02-24 17:25:00,423][08483] Num frames 4000... | |
| [2023-02-24 17:25:00,533][08483] Num frames 4100... | |
| [2023-02-24 17:25:00,645][08483] Num frames 4200... | |
| [2023-02-24 17:25:00,728][08483] Avg episode rewards: #0: 21.808, true rewards: #0: 10.557 | |
| [2023-02-24 17:25:00,731][08483] Avg episode reward: 21.808, avg true_objective: 10.557 | |
| [2023-02-24 17:25:00,817][08483] Num frames 4300... | |
| [2023-02-24 17:25:00,927][08483] Num frames 4400... | |
| [2023-02-24 17:25:01,050][08483] Num frames 4500... | |
| [2023-02-24 17:25:01,163][08483] Num frames 4600... | |
| [2023-02-24 17:25:01,279][08483] Num frames 4700... | |
| [2023-02-24 17:25:01,405][08483] Num frames 4800... | |
| [2023-02-24 17:25:01,565][08483] Num frames 4900... | |
| [2023-02-24 17:25:01,728][08483] Num frames 5000... | |
| [2023-02-24 17:25:01,875][08483] Avg episode rewards: #0: 20.710, true rewards: #0: 10.110 | |
| [2023-02-24 17:25:01,879][08483] Avg episode reward: 20.710, avg true_objective: 10.110 | |
| [2023-02-24 17:25:01,970][08483] Num frames 5100... | |
| [2023-02-24 17:25:02,124][08483] Num frames 5200... | |
| [2023-02-24 17:25:02,286][08483] Num frames 5300... | |
| [2023-02-24 17:25:02,451][08483] Num frames 5400... | |
| [2023-02-24 17:25:02,618][08483] Num frames 5500... | |
| [2023-02-24 17:25:02,778][08483] Num frames 5600... | |
| [2023-02-24 17:25:02,937][08483] Num frames 5700... | |
| [2023-02-24 17:25:03,114][08483] Avg episode rewards: #0: 19.795, true rewards: #0: 9.628 | |
| [2023-02-24 17:25:03,116][08483] Avg episode reward: 19.795, avg true_objective: 9.628 | |
| [2023-02-24 17:25:03,158][08483] Num frames 5800... | |
| [2023-02-24 17:25:03,320][08483] Num frames 5900... | |
| [2023-02-24 17:25:03,479][08483] Num frames 6000... | |
| [2023-02-24 17:25:03,635][08483] Num frames 6100... | |
| [2023-02-24 17:25:03,799][08483] Num frames 6200... | |
| [2023-02-24 17:25:03,959][08483] Num frames 6300... | |
| [2023-02-24 17:25:04,120][08483] Num frames 6400... | |
| [2023-02-24 17:25:04,281][08483] Num frames 6500... | |
| [2023-02-24 17:25:04,452][08483] Num frames 6600... | |
| [2023-02-24 17:25:04,611][08483] Num frames 6700... | |
| [2023-02-24 17:25:04,778][08483] Num frames 6800... | |
| [2023-02-24 17:25:04,915][08483] Num frames 6900... | |
| [2023-02-24 17:25:05,027][08483] Num frames 7000... | |
| [2023-02-24 17:25:05,138][08483] Num frames 7100... | |
| [2023-02-24 17:25:05,260][08483] Num frames 7200... | |
| [2023-02-24 17:25:05,383][08483] Num frames 7300... | |
| [2023-02-24 17:25:05,455][08483] Avg episode rewards: #0: 22.019, true rewards: #0: 10.447 | |
| [2023-02-24 17:25:05,456][08483] Avg episode reward: 22.019, avg true_objective: 10.447 | |
| [2023-02-24 17:25:05,555][08483] Num frames 7400... | |
| [2023-02-24 17:25:05,663][08483] Num frames 7500... | |
| [2023-02-24 17:25:05,777][08483] Num frames 7600... | |
| [2023-02-24 17:25:05,885][08483] Num frames 7700... | |
| [2023-02-24 17:25:05,991][08483] Num frames 7800... | |
| [2023-02-24 17:25:06,143][08483] Avg episode rewards: #0: 20.486, true rewards: #0: 9.861 | |
| [2023-02-24 17:25:06,145][08483] Avg episode reward: 20.486, avg true_objective: 9.861 | |
| [2023-02-24 17:25:06,160][08483] Num frames 7900... | |
| [2023-02-24 17:25:06,280][08483] Num frames 8000... | |
| [2023-02-24 17:25:06,397][08483] Num frames 8100... | |
| [2023-02-24 17:25:06,507][08483] Num frames 8200... | |
| [2023-02-24 17:25:06,618][08483] Num frames 8300... | |
| [2023-02-24 17:25:06,729][08483] Num frames 8400... | |
| [2023-02-24 17:25:06,787][08483] Avg episode rewards: #0: 19.223, true rewards: #0: 9.334 | |
| [2023-02-24 17:25:06,791][08483] Avg episode reward: 19.223, avg true_objective: 9.334 | |
| [2023-02-24 17:25:06,899][08483] Num frames 8500... | |
| [2023-02-24 17:25:07,010][08483] Num frames 8600... | |
| [2023-02-24 17:25:07,123][08483] Num frames 8700... | |
| [2023-02-24 17:25:07,234][08483] Num frames 8800... | |
| [2023-02-24 17:25:07,356][08483] Num frames 8900... | |
| [2023-02-24 17:25:07,469][08483] Num frames 9000... | |
| [2023-02-24 17:25:07,578][08483] Num frames 9100... | |
| [2023-02-24 17:25:07,691][08483] Num frames 9200... | |
| [2023-02-24 17:25:07,809][08483] Num frames 9300... | |
| [2023-02-24 17:25:07,961][08483] Avg episode rewards: #0: 19.291, true rewards: #0: 9.391 | |
| [2023-02-24 17:25:07,963][08483] Avg episode reward: 19.291, avg true_objective: 9.391 | |
| [2023-02-24 17:26:02,840][08483] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |