| [2023-02-22 13:21:44,841][00860] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-22 13:21:44,847][00860] Rollout worker 0 uses device cpu | |
| [2023-02-22 13:21:44,849][00860] Rollout worker 1 uses device cpu | |
| [2023-02-22 13:21:44,855][00860] Rollout worker 2 uses device cpu | |
| [2023-02-22 13:21:44,857][00860] Rollout worker 3 uses device cpu | |
| [2023-02-22 13:21:44,860][00860] Rollout worker 4 uses device cpu | |
| [2023-02-22 13:21:44,861][00860] Rollout worker 5 uses device cpu | |
| [2023-02-22 13:21:44,864][00860] Rollout worker 6 uses device cpu | |
| [2023-02-22 13:21:44,866][00860] Rollout worker 7 uses device cpu | |
| [2023-02-22 13:21:45,067][00860] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-22 13:21:45,068][00860] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-22 13:21:45,104][00860] Starting all processes... | |
| [2023-02-22 13:21:45,107][00860] Starting process learner_proc0 | |
| [2023-02-22 13:21:45,167][00860] Starting all processes... | |
| [2023-02-22 13:21:45,179][00860] Starting process inference_proc0-0 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc0 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc1 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc2 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc3 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc4 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc5 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc6 | |
| [2023-02-22 13:21:45,180][00860] Starting process rollout_proc7 | |
| [2023-02-22 13:21:59,269][14033] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-22 13:21:59,273][14033] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-22 13:21:59,427][14053] Worker 5 uses CPU cores [1] | |
| [2023-02-22 13:21:59,545][14051] Worker 4 uses CPU cores [0] | |
| [2023-02-22 13:21:59,891][14050] Worker 2 uses CPU cores [0] | |
| [2023-02-22 13:21:59,901][14049] Worker 1 uses CPU cores [1] | |
| [2023-02-22 13:21:59,929][14048] Worker 0 uses CPU cores [0] | |
| [2023-02-22 13:21:59,933][14054] Worker 6 uses CPU cores [0] | |
| [2023-02-22 13:22:00,078][14047] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-22 13:22:00,084][14047] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-22 13:22:00,119][14055] Worker 7 uses CPU cores [1] | |
| [2023-02-22 13:22:00,153][14052] Worker 3 uses CPU cores [1] | |
| [2023-02-22 13:22:00,487][14033] Num visible devices: 1 | |
| [2023-02-22 13:22:00,489][14047] Num visible devices: 1 | |
| [2023-02-22 13:22:00,517][14033] Starting seed is not provided | |
| [2023-02-22 13:22:00,518][14033] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-22 13:22:00,519][14033] Initializing actor-critic model on device cuda:0 | |
| [2023-02-22 13:22:00,520][14033] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-22 13:22:00,526][14033] RunningMeanStd input shape: (1,) | |
| [2023-02-22 13:22:00,565][14033] ConvEncoder: input_channels=3 | |
| [2023-02-22 13:22:01,139][14033] Conv encoder output size: 512 | |
| [2023-02-22 13:22:01,141][14033] Policy head output size: 512 | |
| [2023-02-22 13:22:01,242][14033] Created Actor Critic model with architecture: | |
| [2023-02-22 13:22:01,243][14033] 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) | |
| ) | |
| ) | |
| [2023-02-22 13:22:05,059][00860] Heartbeat connected on Batcher_0 | |
| [2023-02-22 13:22:05,067][00860] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-22 13:22:05,080][00860] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-22 13:22:05,085][00860] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-22 13:22:05,090][00860] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-22 13:22:05,094][00860] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-22 13:22:05,097][00860] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-22 13:22:05,099][00860] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-22 13:22:05,100][00860] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-22 13:22:05,104][00860] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-22 13:22:12,135][14033] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-22 13:22:12,136][14033] No checkpoints found | |
| [2023-02-22 13:22:12,136][14033] Did not load from checkpoint, starting from scratch! | |
| [2023-02-22 13:22:12,136][14033] Initialized policy 0 weights for model version 0 | |
| [2023-02-22 13:22:12,142][14033] LearnerWorker_p0 finished initialization! | |
| [2023-02-22 13:22:12,143][14033] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-22 13:22:12,142][00860] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-22 13:22:12,360][14047] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-22 13:22:12,361][14047] RunningMeanStd input shape: (1,) | |
| [2023-02-22 13:22:12,373][14047] ConvEncoder: input_channels=3 | |
| [2023-02-22 13:22:12,471][14047] Conv encoder output size: 512 | |
| [2023-02-22 13:22:12,471][14047] Policy head output size: 512 | |
| [2023-02-22 13:22:14,611][00860] 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) | |
| [2023-02-22 13:22:14,800][00860] Inference worker 0-0 is ready! | |
| [2023-02-22 13:22:14,804][00860] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-22 13:22:14,941][14055] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,946][14048] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,957][14051] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,958][14050] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,955][14054] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,967][14053] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,969][14052] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:14,986][14049] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:22:15,824][14053] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:15,825][14055] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:16,217][14050] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:16,219][14048] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:16,228][14054] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:16,552][14053] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:16,556][14055] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:16,726][14051] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:16,834][14054] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:17,196][14053] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:17,388][14050] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:17,759][14054] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:17,963][14052] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:17,999][14053] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:18,482][14048] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:18,639][14050] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:18,982][14054] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:19,234][14052] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:19,331][14049] Decorrelating experience for 0 frames... | |
| [2023-02-22 13:22:19,611][00860] 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) | |
| [2023-02-22 13:22:19,829][14048] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:19,880][14055] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:19,882][14050] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:20,464][14051] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:20,707][14048] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:20,871][14052] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:21,198][14049] Decorrelating experience for 32 frames... | |
| [2023-02-22 13:22:21,276][14055] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:21,622][14051] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:22,035][14051] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:22,139][14052] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:22,534][14049] Decorrelating experience for 64 frames... | |
| [2023-02-22 13:22:24,615][00860] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 69.4. Samples: 694. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-22 13:22:24,620][00860] Avg episode reward: [(0, '1.227')] | |
| [2023-02-22 13:22:24,738][14049] Decorrelating experience for 96 frames... | |
| [2023-02-22 13:22:29,611][00860] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 132.8. Samples: 1992. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-22 13:22:29,620][00860] Avg episode reward: [(0, '2.421')] | |
| [2023-02-22 13:22:30,022][14033] Signal inference workers to stop experience collection... | |
| [2023-02-22 13:22:30,053][14047] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-22 13:22:33,277][14033] Signal inference workers to resume experience collection... | |
| [2023-02-22 13:22:33,278][14047] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-22 13:22:34,611][00860] Fps is (10 sec: 409.8, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 134.0. Samples: 2680. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-02-22 13:22:34,621][00860] Avg episode reward: [(0, '2.974')] | |
| [2023-02-22 13:22:39,611][00860] Fps is (10 sec: 3276.8, 60 sec: 1310.7, 300 sec: 1310.7). Total num frames: 32768. Throughput: 0: 327.1. Samples: 8178. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:22:39,614][00860] Avg episode reward: [(0, '3.968')] | |
| [2023-02-22 13:22:41,182][14047] Updated weights for policy 0, policy_version 10 (0.0017) | |
| [2023-02-22 13:22:44,611][00860] Fps is (10 sec: 4505.6, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 49152. Throughput: 0: 391.3. Samples: 11738. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:22:44,616][00860] Avg episode reward: [(0, '4.353')] | |
| [2023-02-22 13:22:49,617][00860] Fps is (10 sec: 3274.8, 60 sec: 1872.1, 300 sec: 1872.1). Total num frames: 65536. Throughput: 0: 462.4. Samples: 16188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:22:49,621][00860] Avg episode reward: [(0, '4.374')] | |
| [2023-02-22 13:22:53,890][14047] Updated weights for policy 0, policy_version 20 (0.0035) | |
| [2023-02-22 13:22:54,611][00860] Fps is (10 sec: 3276.8, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 527.4. Samples: 21096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:22:54,619][00860] Avg episode reward: [(0, '4.439')] | |
| [2023-02-22 13:22:59,611][00860] Fps is (10 sec: 3688.7, 60 sec: 2275.6, 300 sec: 2275.6). Total num frames: 102400. Throughput: 0: 544.1. Samples: 24486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:22:59,619][00860] Avg episode reward: [(0, '4.514')] | |
| [2023-02-22 13:22:59,625][14033] Saving new best policy, reward=4.514! | |
| [2023-02-22 13:23:04,617][00860] Fps is (10 sec: 3684.2, 60 sec: 2375.4, 300 sec: 2375.4). Total num frames: 118784. Throughput: 0: 662.9. Samples: 29834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:23:04,627][00860] Avg episode reward: [(0, '4.484')] | |
| [2023-02-22 13:23:04,650][14047] Updated weights for policy 0, policy_version 30 (0.0025) | |
| [2023-02-22 13:23:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 135168. Throughput: 0: 744.7. Samples: 34202. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:23:09,616][00860] Avg episode reward: [(0, '4.419')] | |
| [2023-02-22 13:23:14,611][00860] Fps is (10 sec: 3278.8, 60 sec: 2525.9, 300 sec: 2525.9). Total num frames: 151552. Throughput: 0: 764.9. Samples: 36412. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:23:14,617][00860] Avg episode reward: [(0, '4.322')] | |
| [2023-02-22 13:23:16,870][14047] Updated weights for policy 0, policy_version 40 (0.0012) | |
| [2023-02-22 13:23:19,611][00860] Fps is (10 sec: 4096.0, 60 sec: 2935.5, 300 sec: 2709.7). Total num frames: 176128. Throughput: 0: 882.7. Samples: 42400. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:23:19,614][00860] Avg episode reward: [(0, '4.395')] | |
| [2023-02-22 13:23:24,615][00860] Fps is (10 sec: 4503.8, 60 sec: 3276.8, 300 sec: 2808.5). Total num frames: 196608. Throughput: 0: 920.7. Samples: 49614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:23:24,624][00860] Avg episode reward: [(0, '4.431')] | |
| [2023-02-22 13:23:26,808][14047] Updated weights for policy 0, policy_version 50 (0.0018) | |
| [2023-02-22 13:23:29,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 2785.3). Total num frames: 208896. Throughput: 0: 893.2. Samples: 51932. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:23:29,623][00860] Avg episode reward: [(0, '4.468')] | |
| [2023-02-22 13:23:34,611][00860] Fps is (10 sec: 2048.8, 60 sec: 3549.9, 300 sec: 2713.6). Total num frames: 217088. Throughput: 0: 852.9. Samples: 54564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:23:34,615][00860] Avg episode reward: [(0, '4.488')] | |
| [2023-02-22 13:23:39,611][00860] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 2843.1). Total num frames: 241664. Throughput: 0: 884.2. Samples: 60884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:23:39,620][00860] Avg episode reward: [(0, '4.465')] | |
| [2023-02-22 13:23:39,630][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000059_241664.pth... | |
| [2023-02-22 13:23:40,595][14047] Updated weights for policy 0, policy_version 60 (0.0014) | |
| [2023-02-22 13:23:44,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2867.2). Total num frames: 258048. Throughput: 0: 858.6. Samples: 63124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:23:44,614][00860] Avg episode reward: [(0, '4.593')] | |
| [2023-02-22 13:23:44,618][14033] Saving new best policy, reward=4.593! | |
| [2023-02-22 13:23:49,612][00860] Fps is (10 sec: 2457.4, 60 sec: 3345.3, 300 sec: 2802.5). Total num frames: 266240. Throughput: 0: 829.1. Samples: 67140. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:23:49,615][00860] Avg episode reward: [(0, '4.485')] | |
| [2023-02-22 13:23:54,611][00860] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 2826.2). Total num frames: 282624. Throughput: 0: 812.5. Samples: 70766. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:23:54,614][00860] Avg episode reward: [(0, '4.327')] | |
| [2023-02-22 13:23:55,727][14047] Updated weights for policy 0, policy_version 70 (0.0043) | |
| [2023-02-22 13:23:59,611][00860] Fps is (10 sec: 3277.1, 60 sec: 3276.8, 300 sec: 2847.7). Total num frames: 299008. Throughput: 0: 814.0. Samples: 73042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:23:59,614][00860] Avg episode reward: [(0, '4.184')] | |
| [2023-02-22 13:24:04,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3208.9, 300 sec: 2830.0). Total num frames: 311296. Throughput: 0: 774.4. Samples: 77250. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-22 13:24:04,614][00860] Avg episode reward: [(0, '4.260')] | |
| [2023-02-22 13:24:07,715][14047] Updated weights for policy 0, policy_version 80 (0.0014) | |
| [2023-02-22 13:24:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 2885.0). Total num frames: 331776. Throughput: 0: 755.3. Samples: 83600. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:24:09,617][00860] Avg episode reward: [(0, '4.314')] | |
| [2023-02-22 13:24:14,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 2901.3). Total num frames: 348160. Throughput: 0: 752.4. Samples: 85790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:24:14,618][00860] Avg episode reward: [(0, '4.413')] | |
| [2023-02-22 13:24:19,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2883.6). Total num frames: 360448. Throughput: 0: 793.4. Samples: 90268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:24:19,621][00860] Avg episode reward: [(0, '4.481')] | |
| [2023-02-22 13:24:20,600][14047] Updated weights for policy 0, policy_version 90 (0.0042) | |
| [2023-02-22 13:24:24,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3140.5, 300 sec: 2961.7). Total num frames: 385024. Throughput: 0: 794.5. Samples: 96638. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:24:24,618][00860] Avg episode reward: [(0, '4.303')] | |
| [2023-02-22 13:24:29,326][14047] Updated weights for policy 0, policy_version 100 (0.0016) | |
| [2023-02-22 13:24:29,615][00860] Fps is (10 sec: 4913.3, 60 sec: 3344.8, 300 sec: 3034.0). Total num frames: 409600. Throughput: 0: 823.0. Samples: 100164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:24:29,622][00860] Avg episode reward: [(0, '4.445')] | |
| [2023-02-22 13:24:34,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2984.2). Total num frames: 417792. Throughput: 0: 855.6. Samples: 105642. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:24:34,615][00860] Avg episode reward: [(0, '4.589')] | |
| [2023-02-22 13:24:39,611][00860] Fps is (10 sec: 2048.8, 60 sec: 3140.3, 300 sec: 2966.1). Total num frames: 430080. Throughput: 0: 842.1. Samples: 108660. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:24:39,617][00860] Avg episode reward: [(0, '4.591')] | |
| [2023-02-22 13:24:43,470][14047] Updated weights for policy 0, policy_version 110 (0.0023) | |
| [2023-02-22 13:24:44,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3031.0). Total num frames: 454656. Throughput: 0: 852.2. Samples: 111392. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:24:44,614][00860] Avg episode reward: [(0, '4.483')] | |
| [2023-02-22 13:24:49,611][00860] Fps is (10 sec: 4915.2, 60 sec: 3549.9, 300 sec: 3091.8). Total num frames: 479232. Throughput: 0: 913.2. Samples: 118346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:24:49,620][00860] Avg episode reward: [(0, '4.523')] | |
| [2023-02-22 13:24:53,199][14047] Updated weights for policy 0, policy_version 120 (0.0047) | |
| [2023-02-22 13:24:54,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3097.6). Total num frames: 495616. Throughput: 0: 898.3. Samples: 124022. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:24:54,618][00860] Avg episode reward: [(0, '4.452')] | |
| [2023-02-22 13:24:59,616][00860] Fps is (10 sec: 2047.0, 60 sec: 3344.8, 300 sec: 3028.5). Total num frames: 499712. Throughput: 0: 881.9. Samples: 125482. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:24:59,621][00860] Avg episode reward: [(0, '4.517')] | |
| [2023-02-22 13:25:04,611][00860] Fps is (10 sec: 2048.0, 60 sec: 3413.3, 300 sec: 3035.9). Total num frames: 516096. Throughput: 0: 858.0. Samples: 128880. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:25:04,614][00860] Avg episode reward: [(0, '4.579')] | |
| [2023-02-22 13:25:08,089][14047] Updated weights for policy 0, policy_version 130 (0.0016) | |
| [2023-02-22 13:25:09,611][00860] Fps is (10 sec: 3688.2, 60 sec: 3413.3, 300 sec: 3066.1). Total num frames: 536576. Throughput: 0: 842.8. Samples: 134564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:25:09,620][00860] Avg episode reward: [(0, '4.704')] | |
| [2023-02-22 13:25:09,632][14033] Saving new best policy, reward=4.704! | |
| [2023-02-22 13:25:14,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3094.8). Total num frames: 557056. Throughput: 0: 836.7. Samples: 137810. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:25:14,613][00860] Avg episode reward: [(0, '4.418')] | |
| [2023-02-22 13:25:19,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3077.5). Total num frames: 569344. Throughput: 0: 812.6. Samples: 142210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:25:19,613][00860] Avg episode reward: [(0, '4.501')] | |
| [2023-02-22 13:25:19,969][14047] Updated weights for policy 0, policy_version 140 (0.0032) | |
| [2023-02-22 13:25:24,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3104.3). Total num frames: 589824. Throughput: 0: 855.0. Samples: 147136. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:25:24,614][00860] Avg episode reward: [(0, '4.400')] | |
| [2023-02-22 13:25:29,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3345.3, 300 sec: 3129.8). Total num frames: 610304. Throughput: 0: 874.4. Samples: 150740. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:25:29,614][00860] Avg episode reward: [(0, '4.350')] | |
| [2023-02-22 13:25:29,854][14047] Updated weights for policy 0, policy_version 150 (0.0012) | |
| [2023-02-22 13:25:34,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3153.9). Total num frames: 630784. Throughput: 0: 873.7. Samples: 157662. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:25:34,615][00860] Avg episode reward: [(0, '4.310')] | |
| [2023-02-22 13:25:39,618][00860] Fps is (10 sec: 3274.5, 60 sec: 3549.4, 300 sec: 3136.8). Total num frames: 643072. Throughput: 0: 843.6. Samples: 161992. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:25:39,621][00860] Avg episode reward: [(0, '4.406')] | |
| [2023-02-22 13:25:39,637][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000157_643072.pth... | |
| [2023-02-22 13:25:42,950][14047] Updated weights for policy 0, policy_version 160 (0.0017) | |
| [2023-02-22 13:25:44,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3140.3). Total num frames: 659456. Throughput: 0: 849.5. Samples: 163704. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:25:44,614][00860] Avg episode reward: [(0, '4.488')] | |
| [2023-02-22 13:25:49,611][00860] Fps is (10 sec: 4098.9, 60 sec: 3413.3, 300 sec: 3181.5). Total num frames: 684032. Throughput: 0: 912.7. Samples: 169952. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:25:49,614][00860] Avg episode reward: [(0, '4.519')] | |
| [2023-02-22 13:25:51,936][14047] Updated weights for policy 0, policy_version 170 (0.0018) | |
| [2023-02-22 13:25:54,616][00860] Fps is (10 sec: 4503.3, 60 sec: 3481.3, 300 sec: 3202.3). Total num frames: 704512. Throughput: 0: 937.2. Samples: 176744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:25:54,619][00860] Avg episode reward: [(0, '4.612')] | |
| [2023-02-22 13:25:59,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.7, 300 sec: 3204.0). Total num frames: 720896. Throughput: 0: 914.3. Samples: 178952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:25:59,614][00860] Avg episode reward: [(0, '4.484')] | |
| [2023-02-22 13:26:04,612][00860] Fps is (10 sec: 2868.4, 60 sec: 3618.1, 300 sec: 3187.7). Total num frames: 733184. Throughput: 0: 908.7. Samples: 183104. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:26:04,619][00860] Avg episode reward: [(0, '4.449')] | |
| [2023-02-22 13:26:05,162][14047] Updated weights for policy 0, policy_version 180 (0.0019) | |
| [2023-02-22 13:26:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3207.1). Total num frames: 753664. Throughput: 0: 931.8. Samples: 189066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:26:09,613][00860] Avg episode reward: [(0, '4.705')] | |
| [2023-02-22 13:26:14,611][00860] Fps is (10 sec: 3686.6, 60 sec: 3549.9, 300 sec: 3208.5). Total num frames: 770048. Throughput: 0: 895.9. Samples: 191056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:14,614][00860] Avg episode reward: [(0, '4.740')] | |
| [2023-02-22 13:26:14,626][14033] Saving new best policy, reward=4.740! | |
| [2023-02-22 13:26:17,209][14047] Updated weights for policy 0, policy_version 190 (0.0013) | |
| [2023-02-22 13:26:19,612][00860] Fps is (10 sec: 2866.9, 60 sec: 3549.8, 300 sec: 3193.2). Total num frames: 782336. Throughput: 0: 844.6. Samples: 195668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:19,619][00860] Avg episode reward: [(0, '4.673')] | |
| [2023-02-22 13:26:24,611][00860] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3194.9). Total num frames: 798720. Throughput: 0: 848.4. Samples: 200166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:24,614][00860] Avg episode reward: [(0, '4.532')] | |
| [2023-02-22 13:26:28,913][14047] Updated weights for policy 0, policy_version 200 (0.0021) | |
| [2023-02-22 13:26:29,611][00860] Fps is (10 sec: 3686.8, 60 sec: 3481.6, 300 sec: 3212.6). Total num frames: 819200. Throughput: 0: 869.0. Samples: 202810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:26:29,614][00860] Avg episode reward: [(0, '4.428')] | |
| [2023-02-22 13:26:34,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3245.3). Total num frames: 843776. Throughput: 0: 889.4. Samples: 209974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:34,618][00860] Avg episode reward: [(0, '4.365')] | |
| [2023-02-22 13:26:38,457][14047] Updated weights for policy 0, policy_version 210 (0.0015) | |
| [2023-02-22 13:26:39,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3618.6, 300 sec: 3245.9). Total num frames: 860160. Throughput: 0: 867.3. Samples: 215768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:26:39,617][00860] Avg episode reward: [(0, '4.420')] | |
| [2023-02-22 13:26:44,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3246.5). Total num frames: 876544. Throughput: 0: 867.9. Samples: 218008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:26:44,614][00860] Avg episode reward: [(0, '4.562')] | |
| [2023-02-22 13:26:49,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3232.1). Total num frames: 888832. Throughput: 0: 856.8. Samples: 221660. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:26:49,618][00860] Avg episode reward: [(0, '4.559')] | |
| [2023-02-22 13:26:51,746][14047] Updated weights for policy 0, policy_version 220 (0.0012) | |
| [2023-02-22 13:26:54,611][00860] Fps is (10 sec: 3686.3, 60 sec: 3481.9, 300 sec: 3262.2). Total num frames: 913408. Throughput: 0: 873.4. Samples: 228368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:54,619][00860] Avg episode reward: [(0, '4.408')] | |
| [2023-02-22 13:26:59,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3262.4). Total num frames: 929792. Throughput: 0: 908.4. Samples: 231936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:26:59,618][00860] Avg episode reward: [(0, '4.401')] | |
| [2023-02-22 13:27:02,734][14047] Updated weights for policy 0, policy_version 230 (0.0020) | |
| [2023-02-22 13:27:04,614][00860] Fps is (10 sec: 3275.9, 60 sec: 3549.7, 300 sec: 3262.6). Total num frames: 946176. Throughput: 0: 900.7. Samples: 236202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:27:04,616][00860] Avg episode reward: [(0, '4.480')] | |
| [2023-02-22 13:27:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3262.9). Total num frames: 962560. Throughput: 0: 909.2. Samples: 241080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:27:09,613][00860] Avg episode reward: [(0, '4.749')] | |
| [2023-02-22 13:27:09,632][14033] Saving new best policy, reward=4.749! | |
| [2023-02-22 13:27:13,372][14047] Updated weights for policy 0, policy_version 240 (0.0013) | |
| [2023-02-22 13:27:14,611][00860] Fps is (10 sec: 4097.2, 60 sec: 3618.1, 300 sec: 3346.2). Total num frames: 987136. Throughput: 0: 928.4. Samples: 244590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:27:14,619][00860] Avg episode reward: [(0, '4.809')] | |
| [2023-02-22 13:27:14,622][14033] Saving new best policy, reward=4.809! | |
| [2023-02-22 13:27:19,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3401.8). Total num frames: 1003520. Throughput: 0: 915.9. Samples: 251190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:27:19,617][00860] Avg episode reward: [(0, '4.564')] | |
| [2023-02-22 13:27:24,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 860.9. Samples: 254508. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:27:24,618][00860] Avg episode reward: [(0, '4.412')] | |
| [2023-02-22 13:27:26,366][14047] Updated weights for policy 0, policy_version 250 (0.0012) | |
| [2023-02-22 13:27:29,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 1032192. Throughput: 0: 861.5. Samples: 256774. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:27:29,613][00860] Avg episode reward: [(0, '4.807')] | |
| [2023-02-22 13:27:34,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 1056768. Throughput: 0: 921.7. Samples: 263138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:27:34,619][00860] Avg episode reward: [(0, '4.939')] | |
| [2023-02-22 13:27:34,625][14033] Saving new best policy, reward=4.939! | |
| [2023-02-22 13:27:36,040][14047] Updated weights for policy 0, policy_version 260 (0.0022) | |
| [2023-02-22 13:27:39,615][00860] Fps is (10 sec: 4503.8, 60 sec: 3617.9, 300 sec: 3485.0). Total num frames: 1077248. Throughput: 0: 924.6. Samples: 269978. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:27:39,618][00860] Avg episode reward: [(0, '4.650')] | |
| [2023-02-22 13:27:39,633][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000263_1077248.pth... | |
| [2023-02-22 13:27:39,777][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000059_241664.pth | |
| [2023-02-22 13:27:44,617][00860] Fps is (10 sec: 3684.2, 60 sec: 3617.8, 300 sec: 3485.1). Total num frames: 1093632. Throughput: 0: 894.7. Samples: 272202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:27:44,620][00860] Avg episode reward: [(0, '4.814')] | |
| [2023-02-22 13:27:48,149][14047] Updated weights for policy 0, policy_version 270 (0.0028) | |
| [2023-02-22 13:27:49,611][00860] Fps is (10 sec: 3278.0, 60 sec: 3686.4, 300 sec: 3485.1). Total num frames: 1110016. Throughput: 0: 901.2. Samples: 276752. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:27:49,613][00860] Avg episode reward: [(0, '4.916')] | |
| [2023-02-22 13:27:54,611][00860] Fps is (10 sec: 3278.7, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 1126400. Throughput: 0: 905.1. Samples: 281810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:27:54,614][00860] Avg episode reward: [(0, '5.295')] | |
| [2023-02-22 13:27:54,616][14033] Saving new best policy, reward=5.295! | |
| [2023-02-22 13:27:59,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3471.3). Total num frames: 1142784. Throughput: 0: 895.2. Samples: 284876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:27:59,614][00860] Avg episode reward: [(0, '5.533')] | |
| [2023-02-22 13:27:59,633][14033] Saving new best policy, reward=5.533! | |
| [2023-02-22 13:28:00,214][14047] Updated weights for policy 0, policy_version 280 (0.0029) | |
| [2023-02-22 13:28:04,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3481.8, 300 sec: 3457.3). Total num frames: 1155072. Throughput: 0: 831.0. Samples: 288586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:28:04,619][00860] Avg episode reward: [(0, '5.520')] | |
| [2023-02-22 13:28:09,612][00860] Fps is (10 sec: 2457.4, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 1167360. Throughput: 0: 834.4. Samples: 292056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:28:09,614][00860] Avg episode reward: [(0, '5.217')] | |
| [2023-02-22 13:28:14,611][00860] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3401.8). Total num frames: 1179648. Throughput: 0: 830.6. Samples: 294152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:28:14,613][00860] Avg episode reward: [(0, '5.272')] | |
| [2023-02-22 13:28:15,674][14047] Updated weights for policy 0, policy_version 290 (0.0044) | |
| [2023-02-22 13:28:19,611][00860] Fps is (10 sec: 3686.8, 60 sec: 3345.1, 300 sec: 3415.7). Total num frames: 1204224. Throughput: 0: 821.3. Samples: 300098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:28:19,613][00860] Avg episode reward: [(0, '5.173')] | |
| [2023-02-22 13:28:24,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1224704. Throughput: 0: 809.5. Samples: 306404. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:28:24,614][00860] Avg episode reward: [(0, '5.137')] | |
| [2023-02-22 13:28:26,047][14047] Updated weights for policy 0, policy_version 300 (0.0018) | |
| [2023-02-22 13:28:29,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 1236992. Throughput: 0: 802.9. Samples: 308326. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-22 13:28:29,618][00860] Avg episode reward: [(0, '5.353')] | |
| [2023-02-22 13:28:34,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3429.5). Total num frames: 1253376. Throughput: 0: 801.1. Samples: 312802. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:28:34,621][00860] Avg episode reward: [(0, '5.392')] | |
| [2023-02-22 13:28:38,157][14047] Updated weights for policy 0, policy_version 310 (0.0025) | |
| [2023-02-22 13:28:39,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3277.0, 300 sec: 3443.4). Total num frames: 1273856. Throughput: 0: 822.4. Samples: 318816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:28:39,619][00860] Avg episode reward: [(0, '5.738')] | |
| [2023-02-22 13:28:39,634][14033] Saving new best policy, reward=5.738! | |
| [2023-02-22 13:28:44,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3413.7, 300 sec: 3499.0). Total num frames: 1298432. Throughput: 0: 830.6. Samples: 322254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:28:44,613][00860] Avg episode reward: [(0, '5.790')] | |
| [2023-02-22 13:28:44,615][14033] Saving new best policy, reward=5.790! | |
| [2023-02-22 13:28:47,435][14047] Updated weights for policy 0, policy_version 320 (0.0025) | |
| [2023-02-22 13:28:49,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 1314816. Throughput: 0: 884.9. Samples: 328408. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:28:49,615][00860] Avg episode reward: [(0, '5.615')] | |
| [2023-02-22 13:28:54,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 1331200. Throughput: 0: 909.0. Samples: 332962. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:28:54,615][00860] Avg episode reward: [(0, '5.643')] | |
| [2023-02-22 13:28:59,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3499.0). Total num frames: 1343488. Throughput: 0: 907.0. Samples: 334968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:28:59,614][00860] Avg episode reward: [(0, '5.647')] | |
| [2023-02-22 13:29:00,793][14047] Updated weights for policy 0, policy_version 330 (0.0021) | |
| [2023-02-22 13:29:04,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1363968. Throughput: 0: 901.6. Samples: 340670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:29:04,619][00860] Avg episode reward: [(0, '5.735')] | |
| [2023-02-22 13:29:09,613][00860] Fps is (10 sec: 4095.4, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1384448. Throughput: 0: 901.0. Samples: 346952. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:09,619][00860] Avg episode reward: [(0, '5.909')] | |
| [2023-02-22 13:29:09,631][14033] Saving new best policy, reward=5.909! | |
| [2023-02-22 13:29:11,505][14047] Updated weights for policy 0, policy_version 340 (0.0022) | |
| [2023-02-22 13:29:14,614][00860] Fps is (10 sec: 3685.3, 60 sec: 3686.2, 300 sec: 3526.7). Total num frames: 1400832. Throughput: 0: 905.9. Samples: 349094. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:14,622][00860] Avg episode reward: [(0, '5.616')] | |
| [2023-02-22 13:29:19,611][00860] Fps is (10 sec: 3277.3, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 1417216. Throughput: 0: 908.3. Samples: 353676. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:19,620][00860] Avg episode reward: [(0, '5.725')] | |
| [2023-02-22 13:29:22,456][14047] Updated weights for policy 0, policy_version 350 (0.0019) | |
| [2023-02-22 13:29:24,611][00860] Fps is (10 sec: 4097.2, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1441792. Throughput: 0: 931.8. Samples: 360748. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:24,620][00860] Avg episode reward: [(0, '5.992')] | |
| [2023-02-22 13:29:24,624][14033] Saving new best policy, reward=5.992! | |
| [2023-02-22 13:29:29,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3526.7). Total num frames: 1458176. Throughput: 0: 933.0. Samples: 364238. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:29,618][00860] Avg episode reward: [(0, '6.070')] | |
| [2023-02-22 13:29:29,630][14033] Saving new best policy, reward=6.070! | |
| [2023-02-22 13:29:34,505][14047] Updated weights for policy 0, policy_version 360 (0.0017) | |
| [2023-02-22 13:29:34,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3540.6). Total num frames: 1474560. Throughput: 0: 881.5. Samples: 368074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:29:34,614][00860] Avg episode reward: [(0, '5.723')] | |
| [2023-02-22 13:29:39,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1490944. Throughput: 0: 880.6. Samples: 372590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:29:39,620][00860] Avg episode reward: [(0, '5.761')] | |
| [2023-02-22 13:29:39,631][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_1490944.pth... | |
| [2023-02-22 13:29:39,784][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000157_643072.pth | |
| [2023-02-22 13:29:44,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 1511424. Throughput: 0: 909.1. Samples: 375878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:29:44,613][00860] Avg episode reward: [(0, '6.043')] | |
| [2023-02-22 13:29:44,758][14047] Updated weights for policy 0, policy_version 370 (0.0022) | |
| [2023-02-22 13:29:49,612][00860] Fps is (10 sec: 4505.2, 60 sec: 3686.4, 300 sec: 3526.7). Total num frames: 1536000. Throughput: 0: 943.2. Samples: 383114. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:29:49,616][00860] Avg episode reward: [(0, '6.144')] | |
| [2023-02-22 13:29:49,630][14033] Saving new best policy, reward=6.144! | |
| [2023-02-22 13:29:54,613][00860] Fps is (10 sec: 4095.2, 60 sec: 3686.3, 300 sec: 3568.4). Total num frames: 1552384. Throughput: 0: 915.1. Samples: 388132. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:29:54,618][00860] Avg episode reward: [(0, '6.198')] | |
| [2023-02-22 13:29:54,620][14033] Saving new best policy, reward=6.198! | |
| [2023-02-22 13:29:55,894][14047] Updated weights for policy 0, policy_version 380 (0.0020) | |
| [2023-02-22 13:29:59,613][00860] Fps is (10 sec: 2866.9, 60 sec: 3686.3, 300 sec: 3554.5). Total num frames: 1564672. Throughput: 0: 915.2. Samples: 390276. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:29:59,616][00860] Avg episode reward: [(0, '6.440')] | |
| [2023-02-22 13:29:59,635][14033] Saving new best policy, reward=6.440! | |
| [2023-02-22 13:30:04,611][00860] Fps is (10 sec: 2867.8, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 1581056. Throughput: 0: 904.3. Samples: 394370. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:30:04,614][00860] Avg episode reward: [(0, '6.726')] | |
| [2023-02-22 13:30:04,624][14033] Saving new best policy, reward=6.726! | |
| [2023-02-22 13:30:07,617][14047] Updated weights for policy 0, policy_version 390 (0.0031) | |
| [2023-02-22 13:30:09,611][00860] Fps is (10 sec: 4096.8, 60 sec: 3686.5, 300 sec: 3554.5). Total num frames: 1605632. Throughput: 0: 899.2. Samples: 401210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:30:09,614][00860] Avg episode reward: [(0, '7.173')] | |
| [2023-02-22 13:30:09,630][14033] Saving new best policy, reward=7.173! | |
| [2023-02-22 13:30:14,613][00860] Fps is (10 sec: 4095.1, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 1622016. Throughput: 0: 883.3. Samples: 403988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:30:14,616][00860] Avg episode reward: [(0, '6.925')] | |
| [2023-02-22 13:30:19,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 1634304. Throughput: 0: 895.3. Samples: 408364. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:30:19,618][00860] Avg episode reward: [(0, '6.691')] | |
| [2023-02-22 13:30:20,276][14047] Updated weights for policy 0, policy_version 400 (0.0022) | |
| [2023-02-22 13:30:24,611][00860] Fps is (10 sec: 3277.6, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1654784. Throughput: 0: 919.6. Samples: 413970. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:30:24,619][00860] Avg episode reward: [(0, '6.447')] | |
| [2023-02-22 13:30:29,119][14047] Updated weights for policy 0, policy_version 410 (0.0025) | |
| [2023-02-22 13:30:29,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 1679360. Throughput: 0: 924.4. Samples: 417474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:30:29,619][00860] Avg episode reward: [(0, '6.573')] | |
| [2023-02-22 13:30:34,614][00860] Fps is (10 sec: 4094.7, 60 sec: 3686.2, 300 sec: 3568.4). Total num frames: 1695744. Throughput: 0: 907.6. Samples: 423960. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-22 13:30:34,620][00860] Avg episode reward: [(0, '6.781')] | |
| [2023-02-22 13:30:39,614][00860] Fps is (10 sec: 2866.5, 60 sec: 3618.0, 300 sec: 3554.5). Total num frames: 1708032. Throughput: 0: 869.4. Samples: 427256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:30:39,621][00860] Avg episode reward: [(0, '7.032')] | |
| [2023-02-22 13:30:42,891][14047] Updated weights for policy 0, policy_version 420 (0.0020) | |
| [2023-02-22 13:30:44,611][00860] Fps is (10 sec: 2868.1, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 1724416. Throughput: 0: 871.9. Samples: 429510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:30:44,621][00860] Avg episode reward: [(0, '6.808')] | |
| [2023-02-22 13:30:49,611][00860] Fps is (10 sec: 4096.9, 60 sec: 3549.9, 300 sec: 3540.7). Total num frames: 1748992. Throughput: 0: 936.0. Samples: 436490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:30:49,620][00860] Avg episode reward: [(0, '7.105')] | |
| [2023-02-22 13:30:51,504][14047] Updated weights for policy 0, policy_version 430 (0.0012) | |
| [2023-02-22 13:30:54,611][00860] Fps is (10 sec: 4505.5, 60 sec: 3618.2, 300 sec: 3554.5). Total num frames: 1769472. Throughput: 0: 926.7. Samples: 442912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:30:54,620][00860] Avg episode reward: [(0, '7.901')] | |
| [2023-02-22 13:30:54,625][14033] Saving new best policy, reward=7.901! | |
| [2023-02-22 13:30:59,615][00860] Fps is (10 sec: 3684.9, 60 sec: 3686.3, 300 sec: 3568.3). Total num frames: 1785856. Throughput: 0: 912.1. Samples: 445036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:30:59,618][00860] Avg episode reward: [(0, '8.453')] | |
| [2023-02-22 13:30:59,635][14033] Saving new best policy, reward=8.453! | |
| [2023-02-22 13:31:04,611][00860] Fps is (10 sec: 2867.3, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 1798144. Throughput: 0: 906.4. Samples: 449154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:04,613][00860] Avg episode reward: [(0, '8.676')] | |
| [2023-02-22 13:31:04,623][14033] Saving new best policy, reward=8.676! | |
| [2023-02-22 13:31:04,887][14047] Updated weights for policy 0, policy_version 440 (0.0017) | |
| [2023-02-22 13:31:09,611][00860] Fps is (10 sec: 3278.1, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1818624. Throughput: 0: 923.7. Samples: 455536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:31:09,613][00860] Avg episode reward: [(0, '8.633')] | |
| [2023-02-22 13:31:14,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3582.3). Total num frames: 1839104. Throughput: 0: 903.6. Samples: 458134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:14,614][00860] Avg episode reward: [(0, '9.464')] | |
| [2023-02-22 13:31:14,619][14033] Saving new best policy, reward=9.464! | |
| [2023-02-22 13:31:15,356][14047] Updated weights for policy 0, policy_version 450 (0.0015) | |
| [2023-02-22 13:31:19,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1855488. Throughput: 0: 873.3. Samples: 463254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:31:19,617][00860] Avg episode reward: [(0, '9.092')] | |
| [2023-02-22 13:31:24,611][00860] Fps is (10 sec: 2867.1, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1867776. Throughput: 0: 899.6. Samples: 467734. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:24,614][00860] Avg episode reward: [(0, '9.618')] | |
| [2023-02-22 13:31:24,616][14033] Saving new best policy, reward=9.618! | |
| [2023-02-22 13:31:27,341][14047] Updated weights for policy 0, policy_version 460 (0.0021) | |
| [2023-02-22 13:31:29,611][00860] Fps is (10 sec: 3686.3, 60 sec: 3549.8, 300 sec: 3554.5). Total num frames: 1892352. Throughput: 0: 919.9. Samples: 470904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:31:29,614][00860] Avg episode reward: [(0, '10.808')] | |
| [2023-02-22 13:31:29,628][14033] Saving new best policy, reward=10.808! | |
| [2023-02-22 13:31:34,611][00860] Fps is (10 sec: 4915.3, 60 sec: 3686.6, 300 sec: 3582.3). Total num frames: 1916928. Throughput: 0: 921.6. Samples: 477964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:34,613][00860] Avg episode reward: [(0, '11.205')] | |
| [2023-02-22 13:31:34,618][14033] Saving new best policy, reward=11.205! | |
| [2023-02-22 13:31:37,044][14047] Updated weights for policy 0, policy_version 470 (0.0033) | |
| [2023-02-22 13:31:39,611][00860] Fps is (10 sec: 3686.5, 60 sec: 3686.5, 300 sec: 3568.4). Total num frames: 1929216. Throughput: 0: 892.5. Samples: 483074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:31:39,615][00860] Avg episode reward: [(0, '11.154')] | |
| [2023-02-22 13:31:39,637][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000471_1929216.pth... | |
| [2023-02-22 13:31:39,832][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000263_1077248.pth | |
| [2023-02-22 13:31:44,612][00860] Fps is (10 sec: 2457.3, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1941504. Throughput: 0: 880.3. Samples: 484646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:44,620][00860] Avg episode reward: [(0, '11.694')] | |
| [2023-02-22 13:31:44,622][14033] Saving new best policy, reward=11.694! | |
| [2023-02-22 13:31:49,611][00860] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1961984. Throughput: 0: 900.4. Samples: 489670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:31:49,613][00860] Avg episode reward: [(0, '12.230')] | |
| [2023-02-22 13:31:49,623][14033] Saving new best policy, reward=12.230! | |
| [2023-02-22 13:31:49,897][14047] Updated weights for policy 0, policy_version 480 (0.0024) | |
| [2023-02-22 13:31:54,611][00860] Fps is (10 sec: 4506.1, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1986560. Throughput: 0: 919.3. Samples: 496906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:31:54,614][00860] Avg episode reward: [(0, '11.692')] | |
| [2023-02-22 13:31:59,611][00860] Fps is (10 sec: 4096.1, 60 sec: 3618.4, 300 sec: 3582.3). Total num frames: 2002944. Throughput: 0: 927.9. Samples: 499890. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:31:59,613][00860] Avg episode reward: [(0, '11.847')] | |
| [2023-02-22 13:32:00,227][14047] Updated weights for policy 0, policy_version 490 (0.0013) | |
| [2023-02-22 13:32:04,615][00860] Fps is (10 sec: 3275.4, 60 sec: 3686.1, 300 sec: 3582.2). Total num frames: 2019328. Throughput: 0: 908.8. Samples: 504154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:32:04,618][00860] Avg episode reward: [(0, '12.724')] | |
| [2023-02-22 13:32:04,630][14033] Saving new best policy, reward=12.724! | |
| [2023-02-22 13:32:09,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 2039808. Throughput: 0: 932.2. Samples: 509684. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:32:09,613][00860] Avg episode reward: [(0, '12.044')] | |
| [2023-02-22 13:32:11,381][14047] Updated weights for policy 0, policy_version 500 (0.0016) | |
| [2023-02-22 13:32:14,611][00860] Fps is (10 sec: 3687.9, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 2056192. Throughput: 0: 938.8. Samples: 513150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:32:14,614][00860] Avg episode reward: [(0, '13.299')] | |
| [2023-02-22 13:32:14,617][14033] Saving new best policy, reward=13.299! | |
| [2023-02-22 13:32:19,613][00860] Fps is (10 sec: 3685.8, 60 sec: 3686.3, 300 sec: 3596.1). Total num frames: 2076672. Throughput: 0: 900.3. Samples: 518478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:32:19,615][00860] Avg episode reward: [(0, '13.769')] | |
| [2023-02-22 13:32:19,628][14033] Saving new best policy, reward=13.769! | |
| [2023-02-22 13:32:24,441][14047] Updated weights for policy 0, policy_version 510 (0.0019) | |
| [2023-02-22 13:32:24,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2088960. Throughput: 0: 874.6. Samples: 522432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:32:24,616][00860] Avg episode reward: [(0, '13.562')] | |
| [2023-02-22 13:32:29,611][00860] Fps is (10 sec: 2458.0, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 2101248. Throughput: 0: 880.2. Samples: 524254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:32:29,617][00860] Avg episode reward: [(0, '13.016')] | |
| [2023-02-22 13:32:34,611][00860] Fps is (10 sec: 2457.6, 60 sec: 3276.8, 300 sec: 3512.9). Total num frames: 2113536. Throughput: 0: 850.7. Samples: 527950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:32:34,617][00860] Avg episode reward: [(0, '13.478')] | |
| [2023-02-22 13:32:37,770][14047] Updated weights for policy 0, policy_version 520 (0.0033) | |
| [2023-02-22 13:32:39,611][00860] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3540.7). Total num frames: 2138112. Throughput: 0: 831.7. Samples: 534334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:32:39,619][00860] Avg episode reward: [(0, '12.842')] | |
| [2023-02-22 13:32:44,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 2154496. Throughput: 0: 843.0. Samples: 537824. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:32:44,616][00860] Avg episode reward: [(0, '12.814')] | |
| [2023-02-22 13:32:49,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2166784. Throughput: 0: 823.2. Samples: 541196. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:32:49,614][00860] Avg episode reward: [(0, '12.921')] | |
| [2023-02-22 13:32:50,389][14047] Updated weights for policy 0, policy_version 530 (0.0016) | |
| [2023-02-22 13:32:54,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3526.7). Total num frames: 2183168. Throughput: 0: 809.5. Samples: 546112. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:32:54,613][00860] Avg episode reward: [(0, '14.035')] | |
| [2023-02-22 13:32:54,617][14033] Saving new best policy, reward=14.035! | |
| [2023-02-22 13:32:59,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3568.4). Total num frames: 2207744. Throughput: 0: 808.5. Samples: 549534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:32:59,620][00860] Avg episode reward: [(0, '13.907')] | |
| [2023-02-22 13:33:00,163][14047] Updated weights for policy 0, policy_version 540 (0.0020) | |
| [2023-02-22 13:33:04,611][00860] Fps is (10 sec: 4505.5, 60 sec: 3481.8, 300 sec: 3596.2). Total num frames: 2228224. Throughput: 0: 837.4. Samples: 556158. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:33:04,618][00860] Avg episode reward: [(0, '13.916')] | |
| [2023-02-22 13:33:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3596.1). Total num frames: 2240512. Throughput: 0: 848.9. Samples: 560634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:09,616][00860] Avg episode reward: [(0, '13.189')] | |
| [2023-02-22 13:33:13,174][14047] Updated weights for policy 0, policy_version 550 (0.0015) | |
| [2023-02-22 13:33:14,611][00860] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3568.4). Total num frames: 2256896. Throughput: 0: 857.6. Samples: 562848. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:33:14,623][00860] Avg episode reward: [(0, '12.470')] | |
| [2023-02-22 13:33:19,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3345.2, 300 sec: 3568.4). Total num frames: 2277376. Throughput: 0: 903.0. Samples: 568584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:19,619][00860] Avg episode reward: [(0, '12.729')] | |
| [2023-02-22 13:33:22,729][14047] Updated weights for policy 0, policy_version 560 (0.0024) | |
| [2023-02-22 13:33:24,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3596.1). Total num frames: 2297856. Throughput: 0: 909.4. Samples: 575258. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:24,615][00860] Avg episode reward: [(0, '12.632')] | |
| [2023-02-22 13:33:29,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2314240. Throughput: 0: 880.9. Samples: 577466. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:33:29,618][00860] Avg episode reward: [(0, '12.672')] | |
| [2023-02-22 13:33:34,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2330624. Throughput: 0: 906.0. Samples: 581964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:34,615][00860] Avg episode reward: [(0, '12.736')] | |
| [2023-02-22 13:33:35,471][14047] Updated weights for policy 0, policy_version 570 (0.0024) | |
| [2023-02-22 13:33:39,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2351104. Throughput: 0: 935.0. Samples: 588188. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-22 13:33:39,614][00860] Avg episode reward: [(0, '12.174')] | |
| [2023-02-22 13:33:39,632][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000574_2351104.pth... | |
| [2023-02-22 13:33:39,752][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000364_1490944.pth | |
| [2023-02-22 13:33:44,272][14047] Updated weights for policy 0, policy_version 580 (0.0014) | |
| [2023-02-22 13:33:44,611][00860] Fps is (10 sec: 4505.5, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2375680. Throughput: 0: 933.6. Samples: 591548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:33:44,618][00860] Avg episode reward: [(0, '11.267')] | |
| [2023-02-22 13:33:49,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2387968. Throughput: 0: 914.3. Samples: 597300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:49,618][00860] Avg episode reward: [(0, '12.212')] | |
| [2023-02-22 13:33:54,611][00860] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2400256. Throughput: 0: 894.4. Samples: 600884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:33:54,615][00860] Avg episode reward: [(0, '12.489')] | |
| [2023-02-22 13:33:57,669][14047] Updated weights for policy 0, policy_version 590 (0.0026) | |
| [2023-02-22 13:33:59,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2424832. Throughput: 0: 907.4. Samples: 603682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:33:59,614][00860] Avg episode reward: [(0, '13.531')] | |
| [2023-02-22 13:34:04,611][00860] Fps is (10 sec: 4505.7, 60 sec: 3618.2, 300 sec: 3596.2). Total num frames: 2445312. Throughput: 0: 930.6. Samples: 610460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:34:04,613][00860] Avg episode reward: [(0, '14.251')] | |
| [2023-02-22 13:34:04,626][14033] Saving new best policy, reward=14.251! | |
| [2023-02-22 13:34:07,146][14047] Updated weights for policy 0, policy_version 600 (0.0034) | |
| [2023-02-22 13:34:09,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 2461696. Throughput: 0: 905.6. Samples: 616008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:34:09,618][00860] Avg episode reward: [(0, '15.093')] | |
| [2023-02-22 13:34:09,633][14033] Saving new best policy, reward=15.093! | |
| [2023-02-22 13:34:14,612][00860] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2478080. Throughput: 0: 902.7. Samples: 618088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:34:14,621][00860] Avg episode reward: [(0, '14.898')] | |
| [2023-02-22 13:34:19,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 2494464. Throughput: 0: 916.0. Samples: 623184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:34:19,616][00860] Avg episode reward: [(0, '15.895')] | |
| [2023-02-22 13:34:19,638][14033] Saving new best policy, reward=15.895! | |
| [2023-02-22 13:34:19,977][14047] Updated weights for policy 0, policy_version 610 (0.0012) | |
| [2023-02-22 13:34:24,611][00860] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2514944. Throughput: 0: 908.3. Samples: 629060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:34:24,617][00860] Avg episode reward: [(0, '16.481')] | |
| [2023-02-22 13:34:24,623][14033] Saving new best policy, reward=16.481! | |
| [2023-02-22 13:34:29,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2535424. Throughput: 0: 907.6. Samples: 632388. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:34:29,618][00860] Avg episode reward: [(0, '16.922')] | |
| [2023-02-22 13:34:29,633][14033] Saving new best policy, reward=16.922! | |
| [2023-02-22 13:34:30,836][14047] Updated weights for policy 0, policy_version 620 (0.0025) | |
| [2023-02-22 13:34:34,611][00860] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2547712. Throughput: 0: 878.1. Samples: 636816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:34:34,618][00860] Avg episode reward: [(0, '17.270')] | |
| [2023-02-22 13:34:34,625][14033] Saving new best policy, reward=17.270! | |
| [2023-02-22 13:34:39,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2568192. Throughput: 0: 908.9. Samples: 641784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:34:39,615][00860] Avg episode reward: [(0, '16.633')] | |
| [2023-02-22 13:34:42,076][14047] Updated weights for policy 0, policy_version 630 (0.0014) | |
| [2023-02-22 13:34:44,611][00860] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2588672. Throughput: 0: 923.6. Samples: 645246. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:34:44,614][00860] Avg episode reward: [(0, '15.190')] | |
| [2023-02-22 13:34:49,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2609152. Throughput: 0: 932.4. Samples: 652416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:34:49,619][00860] Avg episode reward: [(0, '15.369')] | |
| [2023-02-22 13:34:52,398][14047] Updated weights for policy 0, policy_version 640 (0.0021) | |
| [2023-02-22 13:34:54,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3596.2). Total num frames: 2625536. Throughput: 0: 908.5. Samples: 656892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:34:54,618][00860] Avg episode reward: [(0, '14.914')] | |
| [2023-02-22 13:34:59,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2641920. Throughput: 0: 910.0. Samples: 659038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:34:59,618][00860] Avg episode reward: [(0, '15.127')] | |
| [2023-02-22 13:35:03,751][14047] Updated weights for policy 0, policy_version 650 (0.0019) | |
| [2023-02-22 13:35:04,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2662400. Throughput: 0: 934.5. Samples: 665236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:35:04,614][00860] Avg episode reward: [(0, '15.443')] | |
| [2023-02-22 13:35:09,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3610.1). Total num frames: 2686976. Throughput: 0: 954.3. Samples: 672004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:35:09,614][00860] Avg episode reward: [(0, '15.358')] | |
| [2023-02-22 13:35:14,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2699264. Throughput: 0: 930.3. Samples: 674252. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:35:14,614][00860] Avg episode reward: [(0, '14.808')] | |
| [2023-02-22 13:35:14,824][14047] Updated weights for policy 0, policy_version 660 (0.0039) | |
| [2023-02-22 13:35:19,612][00860] Fps is (10 sec: 2867.0, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 2715648. Throughput: 0: 929.4. Samples: 678640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:35:19,619][00860] Avg episode reward: [(0, '14.749')] | |
| [2023-02-22 13:35:24,611][00860] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2736128. Throughput: 0: 945.2. Samples: 684316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:35:24,620][00860] Avg episode reward: [(0, '15.971')] | |
| [2023-02-22 13:35:26,296][14047] Updated weights for policy 0, policy_version 670 (0.0013) | |
| [2023-02-22 13:35:29,611][00860] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 2756608. Throughput: 0: 932.9. Samples: 687226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:35:29,619][00860] Avg episode reward: [(0, '15.965')] | |
| [2023-02-22 13:35:34,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3610.1). Total num frames: 2772992. Throughput: 0: 899.8. Samples: 692908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:35:34,619][00860] Avg episode reward: [(0, '16.927')] | |
| [2023-02-22 13:35:38,229][14047] Updated weights for policy 0, policy_version 680 (0.0022) | |
| [2023-02-22 13:35:39,615][00860] Fps is (10 sec: 2866.1, 60 sec: 3617.9, 300 sec: 3596.1). Total num frames: 2785280. Throughput: 0: 898.3. Samples: 697320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:35:39,617][00860] Avg episode reward: [(0, '17.956')] | |
| [2023-02-22 13:35:39,689][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000681_2789376.pth... | |
| [2023-02-22 13:35:39,865][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000471_1929216.pth | |
| [2023-02-22 13:35:39,875][14033] Saving new best policy, reward=17.956! | |
| [2023-02-22 13:35:44,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 2809856. Throughput: 0: 908.1. Samples: 699904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:35:44,619][00860] Avg episode reward: [(0, '18.189')] | |
| [2023-02-22 13:35:44,626][14033] Saving new best policy, reward=18.189! | |
| [2023-02-22 13:35:48,022][14047] Updated weights for policy 0, policy_version 690 (0.0021) | |
| [2023-02-22 13:35:49,613][00860] Fps is (10 sec: 4506.4, 60 sec: 3686.3, 300 sec: 3596.1). Total num frames: 2830336. Throughput: 0: 927.6. Samples: 706982. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:35:49,621][00860] Avg episode reward: [(0, '17.562')] | |
| [2023-02-22 13:35:54,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3610.1). Total num frames: 2850816. Throughput: 0: 903.2. Samples: 712648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:35:54,613][00860] Avg episode reward: [(0, '18.563')] | |
| [2023-02-22 13:35:54,617][14033] Saving new best policy, reward=18.563! | |
| [2023-02-22 13:35:59,614][00860] Fps is (10 sec: 2866.9, 60 sec: 3618.0, 300 sec: 3596.1). Total num frames: 2859008. Throughput: 0: 898.2. Samples: 714672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:35:59,621][00860] Avg episode reward: [(0, '19.110')] | |
| [2023-02-22 13:35:59,635][14033] Saving new best policy, reward=19.110! | |
| [2023-02-22 13:36:01,773][14047] Updated weights for policy 0, policy_version 700 (0.0039) | |
| [2023-02-22 13:36:04,611][00860] Fps is (10 sec: 2457.6, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2875392. Throughput: 0: 883.0. Samples: 718374. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:04,614][00860] Avg episode reward: [(0, '18.471')] | |
| [2023-02-22 13:36:09,611][00860] Fps is (10 sec: 4097.2, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2899968. Throughput: 0: 907.2. Samples: 725142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:36:09,614][00860] Avg episode reward: [(0, '19.350')] | |
| [2023-02-22 13:36:09,628][14033] Saving new best policy, reward=19.350! | |
| [2023-02-22 13:36:11,061][14047] Updated weights for policy 0, policy_version 710 (0.0031) | |
| [2023-02-22 13:36:14,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2916352. Throughput: 0: 913.1. Samples: 728316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:14,616][00860] Avg episode reward: [(0, '20.335')] | |
| [2023-02-22 13:36:14,622][14033] Saving new best policy, reward=20.335! | |
| [2023-02-22 13:36:19,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3610.0). Total num frames: 2932736. Throughput: 0: 881.7. Samples: 732584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:36:19,614][00860] Avg episode reward: [(0, '21.887')] | |
| [2023-02-22 13:36:19,627][14033] Saving new best policy, reward=21.887! | |
| [2023-02-22 13:36:24,098][14047] Updated weights for policy 0, policy_version 720 (0.0032) | |
| [2023-02-22 13:36:24,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2949120. Throughput: 0: 892.3. Samples: 737472. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-22 13:36:24,614][00860] Avg episode reward: [(0, '20.784')] | |
| [2023-02-22 13:36:29,611][00860] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2973696. Throughput: 0: 911.1. Samples: 740904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:29,614][00860] Avg episode reward: [(0, '22.140')] | |
| [2023-02-22 13:36:29,623][14033] Saving new best policy, reward=22.140! | |
| [2023-02-22 13:36:34,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2985984. Throughput: 0: 881.7. Samples: 746658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:34,623][00860] Avg episode reward: [(0, '23.162')] | |
| [2023-02-22 13:36:34,626][14033] Saving new best policy, reward=23.162! | |
| [2023-02-22 13:36:35,071][14047] Updated weights for policy 0, policy_version 730 (0.0025) | |
| [2023-02-22 13:36:39,611][00860] Fps is (10 sec: 2867.3, 60 sec: 3618.4, 300 sec: 3596.2). Total num frames: 3002368. Throughput: 0: 854.6. Samples: 751106. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:36:39,618][00860] Avg episode reward: [(0, '23.666')] | |
| [2023-02-22 13:36:39,635][14033] Saving new best policy, reward=23.666! | |
| [2023-02-22 13:36:44,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 3018752. Throughput: 0: 858.5. Samples: 753300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:44,620][00860] Avg episode reward: [(0, '23.356')] | |
| [2023-02-22 13:36:46,797][14047] Updated weights for policy 0, policy_version 740 (0.0043) | |
| [2023-02-22 13:36:49,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3568.4). Total num frames: 3039232. Throughput: 0: 917.7. Samples: 759670. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:36:49,618][00860] Avg episode reward: [(0, '22.706')] | |
| [2023-02-22 13:36:54,612][00860] Fps is (10 sec: 3686.0, 60 sec: 3413.3, 300 sec: 3568.4). Total num frames: 3055616. Throughput: 0: 871.5. Samples: 764360. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:36:54,615][00860] Avg episode reward: [(0, '22.760')] | |
| [2023-02-22 13:36:59,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3481.8, 300 sec: 3554.5). Total num frames: 3067904. Throughput: 0: 839.0. Samples: 766070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:36:59,614][00860] Avg episode reward: [(0, '22.964')] | |
| [2023-02-22 13:37:00,631][14047] Updated weights for policy 0, policy_version 750 (0.0044) | |
| [2023-02-22 13:37:04,611][00860] Fps is (10 sec: 2457.8, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3080192. Throughput: 0: 829.8. Samples: 769924. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-22 13:37:04,618][00860] Avg episode reward: [(0, '22.465')] | |
| [2023-02-22 13:37:09,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3540.6). Total num frames: 3100672. Throughput: 0: 847.2. Samples: 775594. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:37:09,618][00860] Avg episode reward: [(0, '21.809')] | |
| [2023-02-22 13:37:11,538][14047] Updated weights for policy 0, policy_version 760 (0.0018) | |
| [2023-02-22 13:37:14,611][00860] Fps is (10 sec: 4505.7, 60 sec: 3481.6, 300 sec: 3554.5). Total num frames: 3125248. Throughput: 0: 849.5. Samples: 779132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:37:14,617][00860] Avg episode reward: [(0, '23.452')] | |
| [2023-02-22 13:37:19,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3568.4). Total num frames: 3141632. Throughput: 0: 863.2. Samples: 785502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:19,617][00860] Avg episode reward: [(0, '23.852')] | |
| [2023-02-22 13:37:19,627][14033] Saving new best policy, reward=23.852! | |
| [2023-02-22 13:37:22,675][14047] Updated weights for policy 0, policy_version 770 (0.0029) | |
| [2023-02-22 13:37:24,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 3158016. Throughput: 0: 865.0. Samples: 790032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:24,619][00860] Avg episode reward: [(0, '24.265')] | |
| [2023-02-22 13:37:24,623][14033] Saving new best policy, reward=24.265! | |
| [2023-02-22 13:37:29,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3610.0). Total num frames: 3178496. Throughput: 0: 872.3. Samples: 792554. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:37:29,619][00860] Avg episode reward: [(0, '23.529')] | |
| [2023-02-22 13:37:32,509][14047] Updated weights for policy 0, policy_version 780 (0.0023) | |
| [2023-02-22 13:37:34,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3203072. Throughput: 0: 891.4. Samples: 799782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:34,619][00860] Avg episode reward: [(0, '23.207')] | |
| [2023-02-22 13:37:39,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3219456. Throughput: 0: 921.1. Samples: 805808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:39,616][00860] Avg episode reward: [(0, '23.891')] | |
| [2023-02-22 13:37:39,629][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000786_3219456.pth... | |
| [2023-02-22 13:37:39,845][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000574_2351104.pth | |
| [2023-02-22 13:37:44,063][14047] Updated weights for policy 0, policy_version 790 (0.0013) | |
| [2023-02-22 13:37:44,612][00860] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3235840. Throughput: 0: 930.6. Samples: 807946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:44,615][00860] Avg episode reward: [(0, '23.762')] | |
| [2023-02-22 13:37:49,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3256320. Throughput: 0: 961.5. Samples: 813192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:49,618][00860] Avg episode reward: [(0, '21.927')] | |
| [2023-02-22 13:37:53,324][14047] Updated weights for policy 0, policy_version 800 (0.0017) | |
| [2023-02-22 13:37:54,611][00860] Fps is (10 sec: 4506.1, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3280896. Throughput: 0: 998.0. Samples: 820504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:37:54,613][00860] Avg episode reward: [(0, '22.403')] | |
| [2023-02-22 13:37:59,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3623.9). Total num frames: 3297280. Throughput: 0: 992.2. Samples: 823782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:37:59,618][00860] Avg episode reward: [(0, '22.817')] | |
| [2023-02-22 13:38:04,612][00860] Fps is (10 sec: 3276.5, 60 sec: 3891.1, 300 sec: 3637.8). Total num frames: 3313664. Throughput: 0: 946.6. Samples: 828102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:38:04,619][00860] Avg episode reward: [(0, '20.805')] | |
| [2023-02-22 13:38:05,636][14047] Updated weights for policy 0, policy_version 810 (0.0015) | |
| [2023-02-22 13:38:09,611][00860] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 3334144. Throughput: 0: 971.1. Samples: 833730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:38:09,620][00860] Avg episode reward: [(0, '21.141')] | |
| [2023-02-22 13:38:14,401][14047] Updated weights for policy 0, policy_version 820 (0.0028) | |
| [2023-02-22 13:38:14,611][00860] Fps is (10 sec: 4506.0, 60 sec: 3891.2, 300 sec: 3665.6). Total num frames: 3358720. Throughput: 0: 992.3. Samples: 837206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:38:14,614][00860] Avg episode reward: [(0, '22.957')] | |
| [2023-02-22 13:38:19,614][00860] Fps is (10 sec: 4095.0, 60 sec: 3891.0, 300 sec: 3651.7). Total num frames: 3375104. Throughput: 0: 970.8. Samples: 843472. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:38:19,619][00860] Avg episode reward: [(0, '22.439')] | |
| [2023-02-22 13:38:24,614][00860] Fps is (10 sec: 3275.9, 60 sec: 3891.0, 300 sec: 3651.7). Total num frames: 3391488. Throughput: 0: 935.7. Samples: 847916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:38:24,618][00860] Avg episode reward: [(0, '23.310')] | |
| [2023-02-22 13:38:26,840][14047] Updated weights for policy 0, policy_version 830 (0.0029) | |
| [2023-02-22 13:38:29,611][00860] Fps is (10 sec: 3687.4, 60 sec: 3891.2, 300 sec: 3665.6). Total num frames: 3411968. Throughput: 0: 946.2. Samples: 850524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:38:29,613][00860] Avg episode reward: [(0, '23.931')] | |
| [2023-02-22 13:38:34,611][00860] Fps is (10 sec: 4507.0, 60 sec: 3891.2, 300 sec: 3679.5). Total num frames: 3436544. Throughput: 0: 987.9. Samples: 857646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:38:34,613][00860] Avg episode reward: [(0, '24.249')] | |
| [2023-02-22 13:38:35,608][14047] Updated weights for policy 0, policy_version 840 (0.0014) | |
| [2023-02-22 13:38:39,611][00860] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 3452928. Throughput: 0: 952.4. Samples: 863362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:38:39,617][00860] Avg episode reward: [(0, '23.585')] | |
| [2023-02-22 13:38:44,611][00860] Fps is (10 sec: 2867.1, 60 sec: 3823.0, 300 sec: 3651.7). Total num frames: 3465216. Throughput: 0: 927.1. Samples: 865500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:38:44,619][00860] Avg episode reward: [(0, '23.616')] | |
| [2023-02-22 13:38:48,029][14047] Updated weights for policy 0, policy_version 850 (0.0038) | |
| [2023-02-22 13:38:49,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3485696. Throughput: 0: 946.2. Samples: 870680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:38:49,618][00860] Avg episode reward: [(0, '22.861')] | |
| [2023-02-22 13:38:54,611][00860] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3510272. Throughput: 0: 976.2. Samples: 877660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:38:54,613][00860] Avg episode reward: [(0, '23.031')] | |
| [2023-02-22 13:38:57,428][14047] Updated weights for policy 0, policy_version 860 (0.0018) | |
| [2023-02-22 13:38:59,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3526656. Throughput: 0: 967.7. Samples: 880754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:38:59,615][00860] Avg episode reward: [(0, '21.578')] | |
| [2023-02-22 13:39:04,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3538944. Throughput: 0: 924.3. Samples: 885062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:39:04,620][00860] Avg episode reward: [(0, '22.907')] | |
| [2023-02-22 13:39:09,615][00860] Fps is (10 sec: 3275.7, 60 sec: 3754.5, 300 sec: 3665.5). Total num frames: 3559424. Throughput: 0: 946.1. Samples: 890490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:39:09,620][00860] Avg episode reward: [(0, '23.920')] | |
| [2023-02-22 13:39:09,689][14047] Updated weights for policy 0, policy_version 870 (0.0021) | |
| [2023-02-22 13:39:14,611][00860] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3584000. Throughput: 0: 966.0. Samples: 893992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:39:14,614][00860] Avg episode reward: [(0, '25.861')] | |
| [2023-02-22 13:39:14,619][14033] Saving new best policy, reward=25.861! | |
| [2023-02-22 13:39:19,613][00860] Fps is (10 sec: 4096.6, 60 sec: 3754.7, 300 sec: 3679.4). Total num frames: 3600384. Throughput: 0: 944.0. Samples: 900130. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:39:19,621][00860] Avg episode reward: [(0, '25.082')] | |
| [2023-02-22 13:39:20,284][14047] Updated weights for policy 0, policy_version 880 (0.0012) | |
| [2023-02-22 13:39:24,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3665.6). Total num frames: 3616768. Throughput: 0: 912.1. Samples: 904408. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:39:24,623][00860] Avg episode reward: [(0, '24.538')] | |
| [2023-02-22 13:39:29,611][00860] Fps is (10 sec: 3687.1, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3637248. Throughput: 0: 919.0. Samples: 906856. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:39:29,615][00860] Avg episode reward: [(0, '23.904')] | |
| [2023-02-22 13:39:31,255][14047] Updated weights for policy 0, policy_version 890 (0.0056) | |
| [2023-02-22 13:39:34,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3657728. Throughput: 0: 956.9. Samples: 913740. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:39:34,614][00860] Avg episode reward: [(0, '22.292')] | |
| [2023-02-22 13:39:39,612][00860] Fps is (10 sec: 3686.0, 60 sec: 3686.3, 300 sec: 3679.4). Total num frames: 3674112. Throughput: 0: 928.9. Samples: 919460. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:39:39,615][00860] Avg episode reward: [(0, '21.260')] | |
| [2023-02-22 13:39:39,654][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000898_3678208.pth... | |
| [2023-02-22 13:39:39,841][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000681_2789376.pth | |
| [2023-02-22 13:39:42,655][14047] Updated weights for policy 0, policy_version 900 (0.0030) | |
| [2023-02-22 13:39:44,611][00860] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 3690496. Throughput: 0: 906.0. Samples: 921524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:39:44,616][00860] Avg episode reward: [(0, '21.139')] | |
| [2023-02-22 13:39:49,611][00860] Fps is (10 sec: 3686.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 3710976. Throughput: 0: 922.8. Samples: 926588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:39:49,614][00860] Avg episode reward: [(0, '21.115')] | |
| [2023-02-22 13:39:53,005][14047] Updated weights for policy 0, policy_version 910 (0.0019) | |
| [2023-02-22 13:39:54,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3731456. Throughput: 0: 956.5. Samples: 933528. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:39:54,614][00860] Avg episode reward: [(0, '22.489')] | |
| [2023-02-22 13:39:59,612][00860] Fps is (10 sec: 4095.8, 60 sec: 3754.6, 300 sec: 3693.3). Total num frames: 3751936. Throughput: 0: 947.8. Samples: 936642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:39:59,617][00860] Avg episode reward: [(0, '23.104')] | |
| [2023-02-22 13:40:04,613][00860] Fps is (10 sec: 3276.1, 60 sec: 3754.5, 300 sec: 3651.7). Total num frames: 3764224. Throughput: 0: 905.6. Samples: 940884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:40:04,615][00860] Avg episode reward: [(0, '23.584')] | |
| [2023-02-22 13:40:05,301][14047] Updated weights for policy 0, policy_version 920 (0.0012) | |
| [2023-02-22 13:40:09,611][00860] Fps is (10 sec: 3276.9, 60 sec: 3754.9, 300 sec: 3679.5). Total num frames: 3784704. Throughput: 0: 927.2. Samples: 946134. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-22 13:40:09,619][00860] Avg episode reward: [(0, '23.917')] | |
| [2023-02-22 13:40:14,613][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.3, 300 sec: 3693.3). Total num frames: 3805184. Throughput: 0: 949.1. Samples: 949566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:40:14,615][00860] Avg episode reward: [(0, '24.820')] | |
| [2023-02-22 13:40:14,703][14047] Updated weights for policy 0, policy_version 930 (0.0012) | |
| [2023-02-22 13:40:19,611][00860] Fps is (10 sec: 3686.3, 60 sec: 3686.5, 300 sec: 3679.5). Total num frames: 3821568. Throughput: 0: 932.8. Samples: 955716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-22 13:40:19,616][00860] Avg episode reward: [(0, '24.443')] | |
| [2023-02-22 13:40:24,611][00860] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3837952. Throughput: 0: 900.2. Samples: 959968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:40:24,614][00860] Avg episode reward: [(0, '23.514')] | |
| [2023-02-22 13:40:27,410][14047] Updated weights for policy 0, policy_version 940 (0.0027) | |
| [2023-02-22 13:40:29,611][00860] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3858432. Throughput: 0: 907.3. Samples: 962354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-22 13:40:29,616][00860] Avg episode reward: [(0, '24.380')] | |
| [2023-02-22 13:40:34,611][00860] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.3). Total num frames: 3878912. Throughput: 0: 949.9. Samples: 969334. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:40:34,616][00860] Avg episode reward: [(0, '26.521')] | |
| [2023-02-22 13:40:34,673][14033] Saving new best policy, reward=26.521! | |
| [2023-02-22 13:40:36,669][14047] Updated weights for policy 0, policy_version 950 (0.0013) | |
| [2023-02-22 13:40:39,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3679.5). Total num frames: 3895296. Throughput: 0: 920.6. Samples: 974956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:40:39,614][00860] Avg episode reward: [(0, '25.936')] | |
| [2023-02-22 13:40:44,611][00860] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3911680. Throughput: 0: 899.2. Samples: 977106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:40:44,614][00860] Avg episode reward: [(0, '25.256')] | |
| [2023-02-22 13:40:49,205][14047] Updated weights for policy 0, policy_version 960 (0.0021) | |
| [2023-02-22 13:40:49,611][00860] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3932160. Throughput: 0: 916.9. Samples: 982144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-22 13:40:49,613][00860] Avg episode reward: [(0, '24.931')] | |
| [2023-02-22 13:40:54,611][00860] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3721.2). Total num frames: 3956736. Throughput: 0: 956.6. Samples: 989180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-22 13:40:54,614][00860] Avg episode reward: [(0, '23.842')] | |
| [2023-02-22 13:40:59,106][14047] Updated weights for policy 0, policy_version 970 (0.0019) | |
| [2023-02-22 13:40:59,613][00860] Fps is (10 sec: 4095.2, 60 sec: 3686.3, 300 sec: 3721.1). Total num frames: 3973120. Throughput: 0: 951.6. Samples: 992386. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:40:59,622][00860] Avg episode reward: [(0, '22.311')] | |
| [2023-02-22 13:41:04,611][00860] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3679.5). Total num frames: 3985408. Throughput: 0: 907.9. Samples: 996572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-22 13:41:04,614][00860] Avg episode reward: [(0, '22.251')] | |
| [2023-02-22 13:41:08,973][14033] Stopping Batcher_0... | |
| [2023-02-22 13:41:08,975][14033] Loop batcher_evt_loop terminating... | |
| [2023-02-22 13:41:08,976][00860] Component Batcher_0 stopped! | |
| [2023-02-22 13:41:08,978][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-22 13:41:09,018][14047] Weights refcount: 2 0 | |
| [2023-02-22 13:41:09,028][00860] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-22 13:41:09,032][14047] Stopping InferenceWorker_p0-w0... | |
| [2023-02-22 13:41:09,032][14047] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-22 13:41:09,073][00860] Component RolloutWorker_w2 stopped! | |
| [2023-02-22 13:41:09,083][14052] Stopping RolloutWorker_w3... | |
| [2023-02-22 13:41:09,082][00860] Component RolloutWorker_w6 stopped! | |
| [2023-02-22 13:41:09,083][14054] Stopping RolloutWorker_w6... | |
| [2023-02-22 13:41:09,090][14054] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-22 13:41:09,090][00860] Component RolloutWorker_w3 stopped! | |
| [2023-02-22 13:41:09,099][00860] Component RolloutWorker_w5 stopped! | |
| [2023-02-22 13:41:09,102][14053] Stopping RolloutWorker_w5... | |
| [2023-02-22 13:41:09,072][14050] Stopping RolloutWorker_w2... | |
| [2023-02-22 13:41:09,105][14050] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-22 13:41:09,084][14052] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-22 13:41:09,110][00860] Component RolloutWorker_w1 stopped! | |
| [2023-02-22 13:41:09,112][14049] Stopping RolloutWorker_w1... | |
| [2023-02-22 13:41:09,108][14053] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-22 13:41:09,113][14049] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-22 13:41:09,133][14048] Stopping RolloutWorker_w0... | |
| [2023-02-22 13:41:09,133][00860] Component RolloutWorker_w0 stopped! | |
| [2023-02-22 13:41:09,146][14051] Stopping RolloutWorker_w4... | |
| [2023-02-22 13:41:09,147][14051] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-22 13:41:09,133][14048] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-22 13:41:09,145][00860] Component RolloutWorker_w7 stopped! | |
| [2023-02-22 13:41:09,149][00860] Component RolloutWorker_w4 stopped! | |
| [2023-02-22 13:41:09,152][14055] Stopping RolloutWorker_w7... | |
| [2023-02-22 13:41:09,154][14055] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-22 13:41:09,174][14033] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000786_3219456.pth | |
| [2023-02-22 13:41:09,194][14033] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-22 13:41:09,350][14033] Stopping LearnerWorker_p0... | |
| [2023-02-22 13:41:09,350][14033] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-22 13:41:09,350][00860] Component LearnerWorker_p0 stopped! | |
| [2023-02-22 13:41:09,361][00860] Waiting for process learner_proc0 to stop... | |
| [2023-02-22 13:41:11,213][00860] Waiting for process inference_proc0-0 to join... | |
| [2023-02-22 13:41:11,672][00860] Waiting for process rollout_proc0 to join... | |
| [2023-02-22 13:41:12,041][00860] Waiting for process rollout_proc1 to join... | |
| [2023-02-22 13:41:12,048][00860] Waiting for process rollout_proc2 to join... | |
| [2023-02-22 13:41:12,052][00860] Waiting for process rollout_proc3 to join... | |
| [2023-02-22 13:41:12,054][00860] Waiting for process rollout_proc4 to join... | |
| [2023-02-22 13:41:12,060][00860] Waiting for process rollout_proc5 to join... | |
| [2023-02-22 13:41:12,061][00860] Waiting for process rollout_proc6 to join... | |
| [2023-02-22 13:41:12,063][00860] Waiting for process rollout_proc7 to join... | |
| [2023-02-22 13:41:12,066][00860] Batcher 0 profile tree view: | |
| batching: 26.6088, releasing_batches: 0.0227 | |
| [2023-02-22 13:41:12,068][00860] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 548.5182 | |
| update_model: 8.0717 | |
| weight_update: 0.0014 | |
| one_step: 0.0047 | |
| handle_policy_step: 532.4603 | |
| deserialize: 15.6351, stack: 3.0982, obs_to_device_normalize: 117.4614, forward: 254.6179, send_messages: 27.2985 | |
| prepare_outputs: 87.2825 | |
| to_cpu: 53.8214 | |
| [2023-02-22 13:41:12,071][00860] Learner 0 profile tree view: | |
| misc: 0.0053, prepare_batch: 19.5980 | |
| train: 77.2350 | |
| epoch_init: 0.0057, minibatch_init: 0.0113, losses_postprocess: 0.6428, kl_divergence: 0.5771, after_optimizer: 33.1650 | |
| calculate_losses: 27.4794 | |
| losses_init: 0.0038, forward_head: 1.7566, bptt_initial: 17.9034, tail: 1.1747, advantages_returns: 0.2468, losses: 3.7758 | |
| bptt: 2.3187 | |
| bptt_forward_core: 2.2325 | |
| update: 14.7066 | |
| clip: 1.4307 | |
| [2023-02-22 13:41:12,072][00860] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3434, enqueue_policy_requests: 148.8462, env_step: 852.6392, overhead: 20.2140, complete_rollouts: 7.1031 | |
| save_policy_outputs: 20.4650 | |
| split_output_tensors: 9.5603 | |
| [2023-02-22 13:41:12,074][00860] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3323, enqueue_policy_requests: 151.7121, env_step: 849.1020, overhead: 20.3732, complete_rollouts: 7.2609 | |
| save_policy_outputs: 20.4552 | |
| split_output_tensors: 9.7123 | |
| [2023-02-22 13:41:12,078][00860] Loop Runner_EvtLoop terminating... | |
| [2023-02-22 13:41:12,081][00860] Runner profile tree view: | |
| main_loop: 1166.9777 | |
| [2023-02-22 13:41:12,083][00860] Collected {0: 4005888}, FPS: 3432.7 | |
| [2023-02-22 13:41:12,213][00860] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-22 13:41:12,216][00860] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-22 13:41:12,218][00860] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-22 13:41:12,220][00860] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-22 13:41:12,222][00860] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-22 13:41:12,224][00860] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-22 13:41:12,226][00860] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-22 13:41:12,227][00860] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-22 13:41:12,228][00860] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-22 13:41:12,229][00860] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-22 13:41:12,230][00860] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-22 13:41:12,231][00860] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-22 13:41:12,232][00860] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-22 13:41:12,233][00860] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-22 13:41:12,234][00860] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-22 13:41:12,262][00860] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-22 13:41:12,265][00860] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-22 13:41:12,267][00860] RunningMeanStd input shape: (1,) | |
| [2023-02-22 13:41:12,285][00860] ConvEncoder: input_channels=3 | |
| [2023-02-22 13:41:12,999][00860] Conv encoder output size: 512 | |
| [2023-02-22 13:41:13,000][00860] Policy head output size: 512 | |
| [2023-02-22 13:41:15,468][00860] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-22 13:41:17,052][00860] Num frames 100... | |
| [2023-02-22 13:41:17,236][00860] Num frames 200... | |
| [2023-02-22 13:41:17,416][00860] Num frames 300... | |
| [2023-02-22 13:41:17,615][00860] Num frames 400... | |
| [2023-02-22 13:41:17,825][00860] Num frames 500... | |
| [2023-02-22 13:41:18,019][00860] Num frames 600... | |
| [2023-02-22 13:41:18,224][00860] Num frames 700... | |
| [2023-02-22 13:41:18,355][00860] Avg episode rewards: #0: 13.360, true rewards: #0: 7.360 | |
| [2023-02-22 13:41:18,358][00860] Avg episode reward: 13.360, avg true_objective: 7.360 | |
| [2023-02-22 13:41:18,482][00860] Num frames 800... | |
| [2023-02-22 13:41:18,707][00860] Num frames 900... | |
| [2023-02-22 13:41:18,913][00860] Num frames 1000... | |
| [2023-02-22 13:41:19,105][00860] Num frames 1100... | |
| [2023-02-22 13:41:19,274][00860] Num frames 1200... | |
| [2023-02-22 13:41:19,451][00860] Num frames 1300... | |
| [2023-02-22 13:41:19,625][00860] Num frames 1400... | |
| [2023-02-22 13:41:19,847][00860] Num frames 1500... | |
| [2023-02-22 13:41:20,032][00860] Num frames 1600... | |
| [2023-02-22 13:41:20,204][00860] Num frames 1700... | |
| [2023-02-22 13:41:20,377][00860] Num frames 1800... | |
| [2023-02-22 13:41:20,575][00860] Num frames 1900... | |
| [2023-02-22 13:41:20,662][00860] Avg episode rewards: #0: 21.580, true rewards: #0: 9.580 | |
| [2023-02-22 13:41:20,665][00860] Avg episode reward: 21.580, avg true_objective: 9.580 | |
| [2023-02-22 13:41:20,821][00860] Num frames 2000... | |
| [2023-02-22 13:41:20,988][00860] Num frames 2100... | |
| [2023-02-22 13:41:21,161][00860] Num frames 2200... | |
| [2023-02-22 13:41:21,343][00860] Num frames 2300... | |
| [2023-02-22 13:41:21,537][00860] Num frames 2400... | |
| [2023-02-22 13:41:21,717][00860] Num frames 2500... | |
| [2023-02-22 13:41:21,888][00860] Avg episode rewards: #0: 19.880, true rewards: #0: 8.547 | |
| [2023-02-22 13:41:21,891][00860] Avg episode reward: 19.880, avg true_objective: 8.547 | |
| [2023-02-22 13:41:21,954][00860] Num frames 2600... | |
| [2023-02-22 13:41:22,125][00860] Num frames 2700... | |
| [2023-02-22 13:41:22,300][00860] Num frames 2800... | |
| [2023-02-22 13:41:22,442][00860] Avg episode rewards: #0: 16.130, true rewards: #0: 7.130 | |
| [2023-02-22 13:41:22,444][00860] Avg episode reward: 16.130, avg true_objective: 7.130 | |
| [2023-02-22 13:41:22,525][00860] Num frames 2900... | |
| [2023-02-22 13:41:22,693][00860] Num frames 3000... | |
| [2023-02-22 13:41:22,822][00860] Num frames 3100... | |
| [2023-02-22 13:41:22,937][00860] Num frames 3200... | |
| [2023-02-22 13:41:23,056][00860] Num frames 3300... | |
| [2023-02-22 13:41:23,173][00860] Num frames 3400... | |
| [2023-02-22 13:41:23,289][00860] Num frames 3500... | |
| [2023-02-22 13:41:23,406][00860] Num frames 3600... | |
| [2023-02-22 13:41:23,523][00860] Num frames 3700... | |
| [2023-02-22 13:41:23,644][00860] Num frames 3800... | |
| [2023-02-22 13:41:23,773][00860] Num frames 3900... | |
| [2023-02-22 13:41:23,887][00860] Num frames 4000... | |
| [2023-02-22 13:41:24,002][00860] Num frames 4100... | |
| [2023-02-22 13:41:24,114][00860] Num frames 4200... | |
| [2023-02-22 13:41:24,227][00860] Num frames 4300... | |
| [2023-02-22 13:41:24,347][00860] Num frames 4400... | |
| [2023-02-22 13:41:24,470][00860] Num frames 4500... | |
| [2023-02-22 13:41:24,597][00860] Num frames 4600... | |
| [2023-02-22 13:41:24,667][00860] Avg episode rewards: #0: 22.024, true rewards: #0: 9.224 | |
| [2023-02-22 13:41:24,670][00860] Avg episode reward: 22.024, avg true_objective: 9.224 | |
| [2023-02-22 13:41:24,771][00860] Num frames 4700... | |
| [2023-02-22 13:41:24,889][00860] Num frames 4800... | |
| [2023-02-22 13:41:25,003][00860] Num frames 4900... | |
| [2023-02-22 13:41:25,112][00860] Num frames 5000... | |
| [2023-02-22 13:41:25,223][00860] Num frames 5100... | |
| [2023-02-22 13:41:25,346][00860] Num frames 5200... | |
| [2023-02-22 13:41:25,461][00860] Num frames 5300... | |
| [2023-02-22 13:41:25,571][00860] Num frames 5400... | |
| [2023-02-22 13:41:25,689][00860] Num frames 5500... | |
| [2023-02-22 13:41:25,803][00860] Num frames 5600... | |
| [2023-02-22 13:41:25,916][00860] Num frames 5700... | |
| [2023-02-22 13:41:26,029][00860] Num frames 5800... | |
| [2023-02-22 13:41:26,143][00860] Num frames 5900... | |
| [2023-02-22 13:41:26,263][00860] Num frames 6000... | |
| [2023-02-22 13:41:26,380][00860] Num frames 6100... | |
| [2023-02-22 13:41:26,499][00860] Num frames 6200... | |
| [2023-02-22 13:41:26,642][00860] Avg episode rewards: #0: 25.793, true rewards: #0: 10.460 | |
| [2023-02-22 13:41:26,644][00860] Avg episode reward: 25.793, avg true_objective: 10.460 | |
| [2023-02-22 13:41:26,673][00860] Num frames 6300... | |
| [2023-02-22 13:41:26,784][00860] Num frames 6400... | |
| [2023-02-22 13:41:26,896][00860] Num frames 6500... | |
| [2023-02-22 13:41:27,012][00860] Num frames 6600... | |
| [2023-02-22 13:41:27,132][00860] Num frames 6700... | |
| [2023-02-22 13:41:27,245][00860] Num frames 6800... | |
| [2023-02-22 13:41:27,361][00860] Num frames 6900... | |
| [2023-02-22 13:41:27,480][00860] Num frames 7000... | |
| [2023-02-22 13:41:27,595][00860] Num frames 7100... | |
| [2023-02-22 13:41:27,718][00860] Num frames 7200... | |
| [2023-02-22 13:41:27,883][00860] Avg episode rewards: #0: 25.710, true rewards: #0: 10.424 | |
| [2023-02-22 13:41:27,884][00860] Avg episode reward: 25.710, avg true_objective: 10.424 | |
| [2023-02-22 13:41:27,892][00860] Num frames 7300... | |
| [2023-02-22 13:41:28,013][00860] Num frames 7400... | |
| [2023-02-22 13:41:28,134][00860] Num frames 7500... | |
| [2023-02-22 13:41:28,260][00860] Num frames 7600... | |
| [2023-02-22 13:41:28,372][00860] Num frames 7700... | |
| [2023-02-22 13:41:28,482][00860] Num frames 7800... | |
| [2023-02-22 13:41:28,595][00860] Num frames 7900... | |
| [2023-02-22 13:41:28,713][00860] Num frames 8000... | |
| [2023-02-22 13:41:28,827][00860] Num frames 8100... | |
| [2023-02-22 13:41:28,938][00860] Num frames 8200... | |
| [2023-02-22 13:41:29,057][00860] Num frames 8300... | |
| [2023-02-22 13:41:29,174][00860] Num frames 8400... | |
| [2023-02-22 13:41:29,287][00860] Num frames 8500... | |
| [2023-02-22 13:41:29,403][00860] Num frames 8600... | |
| [2023-02-22 13:41:29,523][00860] Num frames 8700... | |
| [2023-02-22 13:41:29,637][00860] Num frames 8800... | |
| [2023-02-22 13:41:29,754][00860] Num frames 8900... | |
| [2023-02-22 13:41:29,878][00860] Avg episode rewards: #0: 27.326, true rewards: #0: 11.201 | |
| [2023-02-22 13:41:29,880][00860] Avg episode reward: 27.326, avg true_objective: 11.201 | |
| [2023-02-22 13:41:29,924][00860] Num frames 9000... | |
| [2023-02-22 13:41:30,031][00860] Num frames 9100... | |
| [2023-02-22 13:41:30,142][00860] Num frames 9200... | |
| [2023-02-22 13:41:30,256][00860] Num frames 9300... | |
| [2023-02-22 13:41:30,369][00860] Num frames 9400... | |
| [2023-02-22 13:41:30,486][00860] Num frames 9500... | |
| [2023-02-22 13:41:30,603][00860] Num frames 9600... | |
| [2023-02-22 13:41:30,725][00860] Num frames 9700... | |
| [2023-02-22 13:41:30,846][00860] Num frames 9800... | |
| [2023-02-22 13:41:30,962][00860] Num frames 9900... | |
| [2023-02-22 13:41:31,075][00860] Num frames 10000... | |
| [2023-02-22 13:41:31,188][00860] Num frames 10100... | |
| [2023-02-22 13:41:31,301][00860] Num frames 10200... | |
| [2023-02-22 13:41:31,383][00860] Avg episode rewards: #0: 27.691, true rewards: #0: 11.358 | |
| [2023-02-22 13:41:31,385][00860] Avg episode reward: 27.691, avg true_objective: 11.358 | |
| [2023-02-22 13:41:31,478][00860] Num frames 10300... | |
| [2023-02-22 13:41:31,589][00860] Num frames 10400... | |
| [2023-02-22 13:41:31,707][00860] Num frames 10500... | |
| [2023-02-22 13:41:31,831][00860] Num frames 10600... | |
| [2023-02-22 13:41:31,941][00860] Num frames 10700... | |
| [2023-02-22 13:41:32,055][00860] Num frames 10800... | |
| [2023-02-22 13:41:32,168][00860] Num frames 10900... | |
| [2023-02-22 13:41:32,281][00860] Num frames 11000... | |
| [2023-02-22 13:41:32,394][00860] Num frames 11100... | |
| [2023-02-22 13:41:32,508][00860] Num frames 11200... | |
| [2023-02-22 13:41:32,621][00860] Num frames 11300... | |
| [2023-02-22 13:41:32,690][00860] Avg episode rewards: #0: 27.110, true rewards: #0: 11.310 | |
| [2023-02-22 13:41:32,692][00860] Avg episode reward: 27.110, avg true_objective: 11.310 | |
| [2023-02-22 13:42:42,345][00860] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-22 13:42:43,081][00860] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-22 13:42:43,083][00860] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-22 13:42:43,085][00860] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-22 13:42:43,087][00860] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-22 13:42:43,088][00860] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-22 13:42:43,090][00860] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-22 13:42:43,093][00860] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-22 13:42:43,094][00860] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-22 13:42:43,095][00860] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-22 13:42:43,096][00860] Adding new argument 'hf_repository'='ThomasSimonini/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-22 13:42:43,097][00860] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-22 13:42:43,099][00860] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-22 13:42:43,100][00860] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-22 13:42:43,101][00860] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-22 13:42:43,102][00860] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-22 13:42:43,133][00860] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-22 13:42:43,138][00860] RunningMeanStd input shape: (1,) | |
| [2023-02-22 13:42:43,166][00860] ConvEncoder: input_channels=3 | |
| [2023-02-22 13:42:43,235][00860] Conv encoder output size: 512 | |
| [2023-02-22 13:42:43,237][00860] Policy head output size: 512 | |
| [2023-02-22 13:42:43,268][00860] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-22 13:42:44,003][00860] Num frames 100... | |
| [2023-02-22 13:42:44,183][00860] Num frames 200... | |
| [2023-02-22 13:42:44,349][00860] Num frames 300... | |
| [2023-02-22 13:42:44,531][00860] Num frames 400... | |
| [2023-02-22 13:42:44,711][00860] Num frames 500... | |
| [2023-02-22 13:42:44,876][00860] Num frames 600... | |
| [2023-02-22 13:42:45,027][00860] Num frames 700... | |
| [2023-02-22 13:42:45,199][00860] Num frames 800... | |
| [2023-02-22 13:42:45,346][00860] Num frames 900... | |
| [2023-02-22 13:42:45,510][00860] Num frames 1000... | |
| [2023-02-22 13:42:45,662][00860] Num frames 1100... | |
| [2023-02-22 13:42:45,871][00860] Num frames 1200... | |
| [2023-02-22 13:42:46,051][00860] Num frames 1300... | |
| [2023-02-22 13:42:46,241][00860] Avg episode rewards: #0: 36.730, true rewards: #0: 13.730 | |
| [2023-02-22 13:42:46,244][00860] Avg episode reward: 36.730, avg true_objective: 13.730 | |
| [2023-02-22 13:42:46,295][00860] Num frames 1400... | |
| [2023-02-22 13:42:46,487][00860] Num frames 1500... | |
| [2023-02-22 13:42:46,671][00860] Num frames 1600... | |
| [2023-02-22 13:42:46,879][00860] Num frames 1700... | |
| [2023-02-22 13:42:47,071][00860] Num frames 1800... | |
| [2023-02-22 13:42:47,269][00860] Num frames 1900... | |
| [2023-02-22 13:42:47,363][00860] Avg episode rewards: #0: 22.085, true rewards: #0: 9.585 | |
| [2023-02-22 13:42:47,366][00860] Avg episode reward: 22.085, avg true_objective: 9.585 | |
| [2023-02-22 13:42:47,529][00860] Num frames 2000... | |
| [2023-02-22 13:42:47,712][00860] Num frames 2100... | |
| [2023-02-22 13:42:47,908][00860] Num frames 2200... | |
| [2023-02-22 13:42:48,109][00860] Num frames 2300... | |
| [2023-02-22 13:42:48,310][00860] Num frames 2400... | |
| [2023-02-22 13:42:48,537][00860] Avg episode rewards: #0: 18.650, true rewards: #0: 8.317 | |
| [2023-02-22 13:42:48,540][00860] Avg episode reward: 18.650, avg true_objective: 8.317 | |
| [2023-02-22 13:42:48,554][00860] Num frames 2500... | |
| [2023-02-22 13:42:48,737][00860] Num frames 2600... | |
| [2023-02-22 13:42:48,945][00860] Num frames 2700... | |
| [2023-02-22 13:42:49,154][00860] Num frames 2800... | |
| [2023-02-22 13:42:49,357][00860] Num frames 2900... | |
| [2023-02-22 13:42:49,543][00860] Num frames 3000... | |
| [2023-02-22 13:42:49,727][00860] Num frames 3100... | |
| [2023-02-22 13:42:49,926][00860] Num frames 3200... | |
| [2023-02-22 13:42:50,104][00860] Num frames 3300... | |
| [2023-02-22 13:42:50,258][00860] Avg episode rewards: #0: 19.148, true rewards: #0: 8.397 | |
| [2023-02-22 13:42:50,261][00860] Avg episode reward: 19.148, avg true_objective: 8.397 | |
| [2023-02-22 13:42:50,328][00860] Num frames 3400... | |
| [2023-02-22 13:42:50,495][00860] Num frames 3500... | |
| [2023-02-22 13:42:50,654][00860] Num frames 3600... | |
| [2023-02-22 13:42:50,812][00860] Num frames 3700... | |
| [2023-02-22 13:42:50,974][00860] Num frames 3800... | |
| [2023-02-22 13:42:51,137][00860] Num frames 3900... | |
| [2023-02-22 13:42:51,292][00860] Num frames 4000... | |
| [2023-02-22 13:42:51,457][00860] Num frames 4100... | |
| [2023-02-22 13:42:51,619][00860] Num frames 4200... | |
| [2023-02-22 13:42:51,737][00860] Num frames 4300... | |
| [2023-02-22 13:42:51,852][00860] Num frames 4400... | |
| [2023-02-22 13:42:51,973][00860] Num frames 4500... | |
| [2023-02-22 13:42:52,085][00860] Num frames 4600... | |
| [2023-02-22 13:42:52,199][00860] Num frames 4700... | |
| [2023-02-22 13:42:52,312][00860] Num frames 4800... | |
| [2023-02-22 13:42:52,430][00860] Num frames 4900... | |
| [2023-02-22 13:42:52,543][00860] Num frames 5000... | |
| [2023-02-22 13:42:52,644][00860] Avg episode rewards: #0: 23.678, true rewards: #0: 10.078 | |
| [2023-02-22 13:42:52,647][00860] Avg episode reward: 23.678, avg true_objective: 10.078 | |
| [2023-02-22 13:42:52,718][00860] Num frames 5100... | |
| [2023-02-22 13:42:52,830][00860] Num frames 5200... | |
| [2023-02-22 13:42:52,948][00860] Num frames 5300... | |
| [2023-02-22 13:42:53,059][00860] Num frames 5400... | |
| [2023-02-22 13:42:53,171][00860] Num frames 5500... | |
| [2023-02-22 13:42:53,285][00860] Num frames 5600... | |
| [2023-02-22 13:42:53,396][00860] Num frames 5700... | |
| [2023-02-22 13:42:53,510][00860] Num frames 5800... | |
| [2023-02-22 13:42:53,627][00860] Num frames 5900... | |
| [2023-02-22 13:42:53,741][00860] Num frames 6000... | |
| [2023-02-22 13:42:53,853][00860] Num frames 6100... | |
| [2023-02-22 13:42:53,972][00860] Num frames 6200... | |
| [2023-02-22 13:42:54,082][00860] Num frames 6300... | |
| [2023-02-22 13:42:54,251][00860] Avg episode rewards: #0: 25.328, true rewards: #0: 10.662 | |
| [2023-02-22 13:42:54,252][00860] Avg episode reward: 25.328, avg true_objective: 10.662 | |
| [2023-02-22 13:42:54,260][00860] Num frames 6400... | |
| [2023-02-22 13:42:54,371][00860] Num frames 6500... | |
| [2023-02-22 13:42:54,486][00860] Num frames 6600... | |
| [2023-02-22 13:42:54,608][00860] Avg episode rewards: #0: 22.084, true rewards: #0: 9.513 | |
| [2023-02-22 13:42:54,610][00860] Avg episode reward: 22.084, avg true_objective: 9.513 | |
| [2023-02-22 13:42:54,660][00860] Num frames 6700... | |
| [2023-02-22 13:42:54,779][00860] Num frames 6800... | |
| [2023-02-22 13:42:54,898][00860] Num frames 6900... | |
| [2023-02-22 13:42:55,015][00860] Num frames 7000... | |
| [2023-02-22 13:42:55,132][00860] Num frames 7100... | |
| [2023-02-22 13:42:55,246][00860] Num frames 7200... | |
| [2023-02-22 13:42:55,358][00860] Num frames 7300... | |
| [2023-02-22 13:42:55,469][00860] Num frames 7400... | |
| [2023-02-22 13:42:55,583][00860] Num frames 7500... | |
| [2023-02-22 13:42:55,695][00860] Num frames 7600... | |
| [2023-02-22 13:42:55,813][00860] Num frames 7700... | |
| [2023-02-22 13:42:55,926][00860] Num frames 7800... | |
| [2023-02-22 13:42:56,083][00860] Avg episode rewards: #0: 23.860, true rewards: #0: 9.860 | |
| [2023-02-22 13:42:56,085][00860] Avg episode reward: 23.860, avg true_objective: 9.860 | |
| [2023-02-22 13:42:56,103][00860] Num frames 7900... | |
| [2023-02-22 13:42:56,215][00860] Num frames 8000... | |
| [2023-02-22 13:42:56,327][00860] Num frames 8100... | |
| [2023-02-22 13:42:56,442][00860] Num frames 8200... | |
| [2023-02-22 13:42:56,569][00860] Num frames 8300... | |
| [2023-02-22 13:42:56,686][00860] Num frames 8400... | |
| [2023-02-22 13:42:56,798][00860] Num frames 8500... | |
| [2023-02-22 13:42:56,954][00860] Avg episode rewards: #0: 22.547, true rewards: #0: 9.547 | |
| [2023-02-22 13:42:56,956][00860] Avg episode reward: 22.547, avg true_objective: 9.547 | |
| [2023-02-22 13:42:56,968][00860] Num frames 8600... | |
| [2023-02-22 13:42:57,086][00860] Num frames 8700... | |
| [2023-02-22 13:42:57,208][00860] Num frames 8800... | |
| [2023-02-22 13:42:57,319][00860] Num frames 8900... | |
| [2023-02-22 13:42:57,429][00860] Num frames 9000... | |
| [2023-02-22 13:42:57,543][00860] Num frames 9100... | |
| [2023-02-22 13:42:57,638][00860] Avg episode rewards: #0: 21.236, true rewards: #0: 9.136 | |
| [2023-02-22 13:42:57,641][00860] Avg episode reward: 21.236, avg true_objective: 9.136 | |
| [2023-02-22 13:43:53,239][00860] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-22 13:49:49,155][00860] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-22 13:49:49,157][00860] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-22 13:49:49,160][00860] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-22 13:49:49,162][00860] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-22 13:49:49,164][00860] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-22 13:49:49,167][00860] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-22 13:49:49,169][00860] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-22 13:49:49,170][00860] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-22 13:49:49,171][00860] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-22 13:49:49,173][00860] Adding new argument 'hf_repository'='aj555/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-22 13:49:49,174][00860] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-22 13:49:49,175][00860] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-22 13:49:49,176][00860] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-22 13:49:49,178][00860] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-22 13:49:49,179][00860] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-22 13:49:49,207][00860] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-22 13:49:49,210][00860] RunningMeanStd input shape: (1,) | |
| [2023-02-22 13:49:49,224][00860] ConvEncoder: input_channels=3 | |
| [2023-02-22 13:49:49,262][00860] Conv encoder output size: 512 | |
| [2023-02-22 13:49:49,267][00860] Policy head output size: 512 | |
| [2023-02-22 13:49:49,291][00860] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-22 13:49:49,733][00860] Num frames 100... | |
| [2023-02-22 13:49:49,846][00860] Num frames 200... | |
| [2023-02-22 13:49:49,956][00860] Num frames 300... | |
| [2023-02-22 13:49:50,066][00860] Num frames 400... | |
| [2023-02-22 13:49:50,178][00860] Num frames 500... | |
| [2023-02-22 13:49:50,300][00860] Num frames 600... | |
| [2023-02-22 13:49:50,365][00860] Avg episode rewards: #0: 11.080, true rewards: #0: 6.080 | |
| [2023-02-22 13:49:50,368][00860] Avg episode reward: 11.080, avg true_objective: 6.080 | |
| [2023-02-22 13:49:50,473][00860] Num frames 700... | |
| [2023-02-22 13:49:50,592][00860] Num frames 800... | |
| [2023-02-22 13:49:50,713][00860] Num frames 900... | |
| [2023-02-22 13:49:50,841][00860] Num frames 1000... | |
| [2023-02-22 13:49:50,952][00860] Num frames 1100... | |
| [2023-02-22 13:49:51,076][00860] Num frames 1200... | |
| [2023-02-22 13:49:51,194][00860] Num frames 1300... | |
| [2023-02-22 13:49:51,317][00860] Num frames 1400... | |
| [2023-02-22 13:49:51,430][00860] Num frames 1500... | |
| [2023-02-22 13:49:51,527][00860] Avg episode rewards: #0: 15.680, true rewards: #0: 7.680 | |
| [2023-02-22 13:49:51,528][00860] Avg episode reward: 15.680, avg true_objective: 7.680 | |
| [2023-02-22 13:49:51,605][00860] Num frames 1600... | |
| [2023-02-22 13:49:51,717][00860] Num frames 1700... | |
| [2023-02-22 13:49:51,831][00860] Num frames 1800... | |
| [2023-02-22 13:49:51,942][00860] Num frames 1900... | |
| [2023-02-22 13:49:52,054][00860] Num frames 2000... | |
| [2023-02-22 13:49:52,174][00860] Num frames 2100... | |
| [2023-02-22 13:49:52,294][00860] Num frames 2200... | |
| [2023-02-22 13:49:52,413][00860] Num frames 2300... | |
| [2023-02-22 13:49:52,528][00860] Num frames 2400... | |
| [2023-02-22 13:49:52,639][00860] Num frames 2500... | |
| [2023-02-22 13:49:52,754][00860] Num frames 2600... | |
| [2023-02-22 13:49:52,867][00860] Num frames 2700... | |
| [2023-02-22 13:49:52,981][00860] Num frames 2800... | |
| [2023-02-22 13:49:53,097][00860] Num frames 2900... | |
| [2023-02-22 13:49:53,210][00860] Num frames 3000... | |
| [2023-02-22 13:49:53,324][00860] Num frames 3100... | |
| [2023-02-22 13:49:53,421][00860] Avg episode rewards: #0: 23.433, true rewards: #0: 10.433 | |
| [2023-02-22 13:49:53,423][00860] Avg episode reward: 23.433, avg true_objective: 10.433 | |
| [2023-02-22 13:49:53,501][00860] Num frames 3200... | |
| [2023-02-22 13:49:53,616][00860] Num frames 3300... | |
| [2023-02-22 13:49:53,742][00860] Num frames 3400... | |
| [2023-02-22 13:49:53,858][00860] Num frames 3500... | |
| [2023-02-22 13:49:53,966][00860] Num frames 3600... | |
| [2023-02-22 13:49:54,076][00860] Num frames 3700... | |
| [2023-02-22 13:49:54,188][00860] Num frames 3800... | |
| [2023-02-22 13:49:54,302][00860] Num frames 3900... | |
| [2023-02-22 13:49:54,427][00860] Num frames 4000... | |
| [2023-02-22 13:49:54,541][00860] Num frames 4100... | |
| [2023-02-22 13:49:54,652][00860] Num frames 4200... | |
| [2023-02-22 13:49:54,762][00860] Num frames 4300... | |
| [2023-02-22 13:49:54,881][00860] Num frames 4400... | |
| [2023-02-22 13:49:54,991][00860] Num frames 4500... | |
| [2023-02-22 13:49:55,105][00860] Num frames 4600... | |
| [2023-02-22 13:49:55,225][00860] Num frames 4700... | |
| [2023-02-22 13:49:55,291][00860] Avg episode rewards: #0: 27.520, true rewards: #0: 11.770 | |
| [2023-02-22 13:49:55,293][00860] Avg episode reward: 27.520, avg true_objective: 11.770 | |
| [2023-02-22 13:49:55,403][00860] Num frames 4800... | |
| [2023-02-22 13:49:55,563][00860] Num frames 4900... | |
| [2023-02-22 13:49:55,714][00860] Num frames 5000... | |
| [2023-02-22 13:49:55,871][00860] Num frames 5100... | |
| [2023-02-22 13:49:56,022][00860] Num frames 5200... | |
| [2023-02-22 13:49:56,177][00860] Num frames 5300... | |
| [2023-02-22 13:49:56,327][00860] Num frames 5400... | |
| [2023-02-22 13:49:56,508][00860] Num frames 5500... | |
| [2023-02-22 13:49:56,667][00860] Num frames 5600... | |
| [2023-02-22 13:49:56,820][00860] Num frames 5700... | |
| [2023-02-22 13:49:56,975][00860] Num frames 5800... | |
| [2023-02-22 13:49:57,129][00860] Num frames 5900... | |
| [2023-02-22 13:49:57,284][00860] Num frames 6000... | |
| [2023-02-22 13:49:57,440][00860] Num frames 6100... | |
| [2023-02-22 13:49:57,605][00860] Num frames 6200... | |
| [2023-02-22 13:49:57,770][00860] Num frames 6300... | |
| [2023-02-22 13:49:57,929][00860] Num frames 6400... | |
| [2023-02-22 13:49:58,090][00860] Num frames 6500... | |
| [2023-02-22 13:49:58,256][00860] Num frames 6600... | |
| [2023-02-22 13:49:58,418][00860] Num frames 6700... | |
| [2023-02-22 13:49:58,578][00860] Num frames 6800... | |
| [2023-02-22 13:49:58,648][00860] Avg episode rewards: #0: 33.216, true rewards: #0: 13.616 | |
| [2023-02-22 13:49:58,649][00860] Avg episode reward: 33.216, avg true_objective: 13.616 | |
| [2023-02-22 13:49:58,786][00860] Num frames 6900... | |
| [2023-02-22 13:49:58,932][00860] Num frames 7000... | |
| [2023-02-22 13:49:59,045][00860] Num frames 7100... | |
| [2023-02-22 13:49:59,183][00860] Num frames 7200... | |
| [2023-02-22 13:49:59,309][00860] Num frames 7300... | |
| [2023-02-22 13:49:59,429][00860] Num frames 7400... | |
| [2023-02-22 13:49:59,548][00860] Num frames 7500... | |
| [2023-02-22 13:49:59,663][00860] Num frames 7600... | |
| [2023-02-22 13:49:59,779][00860] Num frames 7700... | |
| [2023-02-22 13:49:59,890][00860] Num frames 7800... | |
| [2023-02-22 13:50:00,032][00860] Avg episode rewards: #0: 32.131, true rewards: #0: 13.132 | |
| [2023-02-22 13:50:00,034][00860] Avg episode reward: 32.131, avg true_objective: 13.132 | |
| [2023-02-22 13:50:00,062][00860] Num frames 7900... | |
| [2023-02-22 13:50:00,179][00860] Num frames 8000... | |
| [2023-02-22 13:50:00,293][00860] Num frames 8100... | |
| [2023-02-22 13:50:00,402][00860] Num frames 8200... | |
| [2023-02-22 13:50:00,525][00860] Num frames 8300... | |
| [2023-02-22 13:50:00,639][00860] Num frames 8400... | |
| [2023-02-22 13:50:00,750][00860] Num frames 8500... | |
| [2023-02-22 13:50:00,862][00860] Num frames 8600... | |
| [2023-02-22 13:50:00,970][00860] Avg episode rewards: #0: 29.638, true rewards: #0: 12.353 | |
| [2023-02-22 13:50:00,972][00860] Avg episode reward: 29.638, avg true_objective: 12.353 | |
| [2023-02-22 13:50:01,036][00860] Num frames 8700... | |
| [2023-02-22 13:50:01,148][00860] Num frames 8800... | |
| [2023-02-22 13:50:01,261][00860] Num frames 8900... | |
| [2023-02-22 13:50:01,375][00860] Num frames 9000... | |
| [2023-02-22 13:50:01,501][00860] Num frames 9100... | |
| [2023-02-22 13:50:01,634][00860] Num frames 9200... | |
| [2023-02-22 13:50:01,756][00860] Num frames 9300... | |
| [2023-02-22 13:50:01,880][00860] Num frames 9400... | |
| [2023-02-22 13:50:02,003][00860] Num frames 9500... | |
| [2023-02-22 13:50:02,074][00860] Avg episode rewards: #0: 28.639, true rewards: #0: 11.889 | |
| [2023-02-22 13:50:02,076][00860] Avg episode reward: 28.639, avg true_objective: 11.889 | |
| [2023-02-22 13:50:02,196][00860] Num frames 9600... | |
| [2023-02-22 13:50:02,319][00860] Num frames 9700... | |
| [2023-02-22 13:50:02,442][00860] Num frames 9800... | |
| [2023-02-22 13:50:02,575][00860] Num frames 9900... | |
| [2023-02-22 13:50:02,702][00860] Num frames 10000... | |
| [2023-02-22 13:50:02,825][00860] Num frames 10100... | |
| [2023-02-22 13:50:02,957][00860] Num frames 10200... | |
| [2023-02-22 13:50:03,083][00860] Num frames 10300... | |
| [2023-02-22 13:50:03,208][00860] Num frames 10400... | |
| [2023-02-22 13:50:03,313][00860] Avg episode rewards: #0: 27.599, true rewards: #0: 11.599 | |
| [2023-02-22 13:50:03,316][00860] Avg episode reward: 27.599, avg true_objective: 11.599 | |
| [2023-02-22 13:50:03,400][00860] Num frames 10500... | |
| [2023-02-22 13:50:03,528][00860] Num frames 10600... | |
| [2023-02-22 13:50:03,664][00860] Num frames 10700... | |
| [2023-02-22 13:50:03,775][00860] Num frames 10800... | |
| [2023-02-22 13:50:03,884][00860] Num frames 10900... | |
| [2023-02-22 13:50:04,000][00860] Num frames 11000... | |
| [2023-02-22 13:50:04,115][00860] Num frames 11100... | |
| [2023-02-22 13:50:04,229][00860] Num frames 11200... | |
| [2023-02-22 13:50:04,339][00860] Num frames 11300... | |
| [2023-02-22 13:50:04,460][00860] Num frames 11400... | |
| [2023-02-22 13:50:04,575][00860] Num frames 11500... | |
| [2023-02-22 13:50:04,698][00860] Num frames 11600... | |
| [2023-02-22 13:50:04,779][00860] Avg episode rewards: #0: 27.623, true rewards: #0: 11.623 | |
| [2023-02-22 13:50:04,781][00860] Avg episode reward: 27.623, avg true_objective: 11.623 | |
| [2023-02-22 13:51:18,282][00860] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |