diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1134 @@ +[2023-02-26 11:56:49,884][00595] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-02-26 11:56:49,886][00595] Rollout worker 0 uses device cpu +[2023-02-26 11:56:49,888][00595] Rollout worker 1 uses device cpu +[2023-02-26 11:56:49,893][00595] Rollout worker 2 uses device cpu +[2023-02-26 11:56:49,894][00595] Rollout worker 3 uses device cpu +[2023-02-26 11:56:49,903][00595] Rollout worker 4 uses device cpu +[2023-02-26 11:56:49,904][00595] Rollout worker 5 uses device cpu +[2023-02-26 11:56:49,905][00595] Rollout worker 6 uses device cpu +[2023-02-26 11:56:49,911][00595] Rollout worker 7 uses device cpu +[2023-02-26 11:56:50,344][00595] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-26 11:56:50,353][00595] InferenceWorker_p0-w0: min num requests: 2 +[2023-02-26 11:56:50,467][00595] Starting all processes... +[2023-02-26 11:56:50,478][00595] Starting process learner_proc0 +[2023-02-26 11:56:50,655][00595] Starting all processes... +[2023-02-26 11:56:50,716][00595] Starting process inference_proc0-0 +[2023-02-26 11:56:50,718][00595] Starting process rollout_proc0 +[2023-02-26 11:56:50,718][00595] Starting process rollout_proc1 +[2023-02-26 11:56:50,721][00595] Starting process rollout_proc2 +[2023-02-26 11:56:50,721][00595] Starting process rollout_proc3 +[2023-02-26 11:56:50,721][00595] Starting process rollout_proc4 +[2023-02-26 11:56:50,756][00595] Starting process rollout_proc5 +[2023-02-26 11:56:50,756][00595] Starting process rollout_proc6 +[2023-02-26 11:56:50,757][00595] Starting process rollout_proc7 +[2023-02-26 11:57:01,854][10641] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-26 11:57:01,863][10641] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-02-26 11:57:01,891][10658] Worker 2 uses CPU cores [0] +[2023-02-26 11:57:01,983][10664] Worker 6 uses CPU cores [0] +[2023-02-26 11:57:02,035][10654] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-26 11:57:02,035][10654] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-02-26 11:57:02,211][10659] Worker 3 uses CPU cores [1] +[2023-02-26 11:57:02,303][10657] Worker 1 uses CPU cores [1] +[2023-02-26 11:57:02,409][10660] Worker 4 uses CPU cores [0] +[2023-02-26 11:57:02,606][10661] Worker 5 uses CPU cores [1] +[2023-02-26 11:57:02,622][10667] Worker 7 uses CPU cores [1] +[2023-02-26 11:57:02,823][10656] Worker 0 uses CPU cores [0] +[2023-02-26 11:57:02,926][10654] Num visible devices: 1 +[2023-02-26 11:57:02,930][10641] Num visible devices: 1 +[2023-02-26 11:57:02,945][10641] Starting seed is not provided +[2023-02-26 11:57:02,945][10641] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-26 11:57:02,946][10641] Initializing actor-critic model on device cuda:0 +[2023-02-26 11:57:02,947][10641] RunningMeanStd input shape: (3, 72, 128) +[2023-02-26 11:57:02,949][10641] RunningMeanStd input shape: (1,) +[2023-02-26 11:57:02,968][10641] ConvEncoder: input_channels=3 +[2023-02-26 11:57:03,431][10641] Conv encoder output size: 512 +[2023-02-26 11:57:03,432][10641] Policy head output size: 512 +[2023-02-26 11:57:03,509][10641] Created Actor Critic model with architecture: +[2023-02-26 11:57:03,510][10641] 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) + ) +) +[2023-02-26 11:57:10,326][00595] Heartbeat connected on Batcher_0 +[2023-02-26 11:57:10,345][00595] Heartbeat connected on InferenceWorker_p0-w0 +[2023-02-26 11:57:10,372][00595] Heartbeat connected on RolloutWorker_w0 +[2023-02-26 11:57:10,376][00595] Heartbeat connected on RolloutWorker_w1 +[2023-02-26 11:57:10,387][00595] Heartbeat connected on RolloutWorker_w2 +[2023-02-26 11:57:10,419][00595] Heartbeat connected on RolloutWorker_w3 +[2023-02-26 11:57:10,430][00595] Heartbeat connected on RolloutWorker_w4 +[2023-02-26 11:57:10,446][00595] Heartbeat connected on RolloutWorker_w5 +[2023-02-26 11:57:10,454][00595] Heartbeat connected on RolloutWorker_w6 +[2023-02-26 11:57:10,465][00595] Heartbeat connected on RolloutWorker_w7 +[2023-02-26 11:57:12,900][10641] Using optimizer +[2023-02-26 11:57:12,901][10641] No checkpoints found +[2023-02-26 11:57:12,901][10641] Did not load from checkpoint, starting from scratch! +[2023-02-26 11:57:12,902][10641] Initialized policy 0 weights for model version 0 +[2023-02-26 11:57:12,905][10641] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-26 11:57:12,911][10641] LearnerWorker_p0 finished initialization! +[2023-02-26 11:57:12,912][00595] Heartbeat connected on LearnerWorker_p0 +[2023-02-26 11:57:13,105][10654] RunningMeanStd input shape: (3, 72, 128) +[2023-02-26 11:57:13,106][10654] RunningMeanStd input shape: (1,) +[2023-02-26 11:57:13,124][10654] ConvEncoder: input_channels=3 +[2023-02-26 11:57:13,221][10654] Conv encoder output size: 512 +[2023-02-26 11:57:13,222][10654] Policy head output size: 512 +[2023-02-26 11:57:14,833][00595] 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) +[2023-02-26 11:57:15,474][00595] Inference worker 0-0 is ready! +[2023-02-26 11:57:15,476][00595] All inference workers are ready! Signal rollout workers to start! +[2023-02-26 11:57:15,603][10656] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,620][10658] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,629][10664] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,630][10660] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,640][10659] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,642][10657] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,643][10661] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:15,644][10667] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 11:57:16,820][10656] Decorrelating experience for 0 frames... +[2023-02-26 11:57:16,822][10658] Decorrelating experience for 0 frames... +[2023-02-26 11:57:16,823][10664] Decorrelating experience for 0 frames... +[2023-02-26 11:57:16,823][10659] Decorrelating experience for 0 frames... +[2023-02-26 11:57:16,820][10657] Decorrelating experience for 0 frames... +[2023-02-26 11:57:16,825][10661] Decorrelating experience for 0 frames... +[2023-02-26 11:57:17,826][10656] Decorrelating experience for 32 frames... +[2023-02-26 11:57:17,827][10658] Decorrelating experience for 32 frames... +[2023-02-26 11:57:17,840][10664] Decorrelating experience for 32 frames... +[2023-02-26 11:57:17,848][10667] Decorrelating experience for 0 frames... +[2023-02-26 11:57:17,854][10661] Decorrelating experience for 32 frames... +[2023-02-26 11:57:17,865][10657] Decorrelating experience for 32 frames... +[2023-02-26 11:57:19,116][10659] Decorrelating experience for 32 frames... +[2023-02-26 11:57:19,127][10667] Decorrelating experience for 32 frames... +[2023-02-26 11:57:19,681][10660] Decorrelating experience for 0 frames... +[2023-02-26 11:57:19,832][00595] 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) +[2023-02-26 11:57:19,983][10659] Decorrelating experience for 64 frames... +[2023-02-26 11:57:19,984][10656] Decorrelating experience for 64 frames... +[2023-02-26 11:57:19,995][10658] Decorrelating experience for 64 frames... +[2023-02-26 11:57:20,010][10664] Decorrelating experience for 64 frames... +[2023-02-26 11:57:21,002][10660] Decorrelating experience for 32 frames... +[2023-02-26 11:57:21,290][10658] Decorrelating experience for 96 frames... +[2023-02-26 11:57:21,291][10664] Decorrelating experience for 96 frames... +[2023-02-26 11:57:21,863][10657] Decorrelating experience for 64 frames... +[2023-02-26 11:57:21,914][10661] Decorrelating experience for 64 frames... +[2023-02-26 11:57:22,482][10659] Decorrelating experience for 96 frames... +[2023-02-26 11:57:23,213][10660] Decorrelating experience for 64 frames... +[2023-02-26 11:57:23,301][10657] Decorrelating experience for 96 frames... +[2023-02-26 11:57:23,331][10661] Decorrelating experience for 96 frames... +[2023-02-26 11:57:23,656][10667] Decorrelating experience for 64 frames... +[2023-02-26 11:57:24,052][10667] Decorrelating experience for 96 frames... +[2023-02-26 11:57:24,240][10656] Decorrelating experience for 96 frames... +[2023-02-26 11:57:24,537][10660] Decorrelating experience for 96 frames... +[2023-02-26 11:57:24,832][00595] 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) +[2023-02-26 11:57:29,057][10641] Signal inference workers to stop experience collection... +[2023-02-26 11:57:29,081][10654] InferenceWorker_p0-w0: stopping experience collection +[2023-02-26 11:57:29,832][00595] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 60.4. Samples: 906. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-26 11:57:29,835][00595] Avg episode reward: [(0, '1.669')] +[2023-02-26 11:57:31,783][10641] Signal inference workers to resume experience collection... +[2023-02-26 11:57:31,784][10654] InferenceWorker_p0-w0: resuming experience collection +[2023-02-26 11:57:34,833][00595] Fps is (10 sec: 1638.4, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 159.6. Samples: 3192. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-26 11:57:34,838][00595] Avg episode reward: [(0, '3.264')] +[2023-02-26 11:57:39,832][00595] Fps is (10 sec: 3276.8, 60 sec: 1310.7, 300 sec: 1310.7). Total num frames: 32768. Throughput: 0: 348.2. Samples: 8706. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-26 11:57:39,836][00595] Avg episode reward: [(0, '3.830')] +[2023-02-26 11:57:42,261][10654] Updated weights for policy 0, policy_version 10 (0.0017) +[2023-02-26 11:57:44,832][00595] Fps is (10 sec: 2867.3, 60 sec: 1501.9, 300 sec: 1501.9). Total num frames: 45056. Throughput: 0: 367.0. Samples: 11010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:57:44,835][00595] Avg episode reward: [(0, '4.329')] +[2023-02-26 11:57:49,832][00595] Fps is (10 sec: 3686.5, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 477.0. Samples: 16694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:57:49,840][00595] Avg episode reward: [(0, '4.448')] +[2023-02-26 11:57:52,073][10654] Updated weights for policy 0, policy_version 20 (0.0026) +[2023-02-26 11:57:54,833][00595] Fps is (10 sec: 4915.0, 60 sec: 2355.2, 300 sec: 2355.2). Total num frames: 94208. Throughput: 0: 598.0. Samples: 23920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 11:57:54,836][00595] Avg episode reward: [(0, '4.452')] +[2023-02-26 11:57:59,834][00595] Fps is (10 sec: 4095.2, 60 sec: 2457.5, 300 sec: 2457.5). Total num frames: 110592. Throughput: 0: 594.5. Samples: 26752. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-26 11:57:59,837][00595] Avg episode reward: [(0, '4.421')] +[2023-02-26 11:57:59,843][10641] Saving new best policy, reward=4.421! +[2023-02-26 11:58:03,337][10654] Updated weights for policy 0, policy_version 30 (0.0021) +[2023-02-26 11:58:04,832][00595] Fps is (10 sec: 2867.3, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 693.6. Samples: 31212. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-26 11:58:04,839][00595] Avg episode reward: [(0, '4.336')] +[2023-02-26 11:58:09,832][00595] Fps is (10 sec: 3277.5, 60 sec: 2606.6, 300 sec: 2606.6). Total num frames: 143360. Throughput: 0: 821.6. Samples: 36972. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-26 11:58:09,840][00595] Avg episode reward: [(0, '4.389')] +[2023-02-26 11:58:13,349][10654] Updated weights for policy 0, policy_version 40 (0.0011) +[2023-02-26 11:58:14,832][00595] Fps is (10 sec: 4505.6, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 880.1. Samples: 40510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:14,835][00595] Avg episode reward: [(0, '4.601')] +[2023-02-26 11:58:14,847][10641] Saving new best policy, reward=4.601! +[2023-02-26 11:58:19,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 954.9. Samples: 46160. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:19,838][00595] Avg episode reward: [(0, '4.527')] +[2023-02-26 11:58:24,833][00595] Fps is (10 sec: 3276.7, 60 sec: 3345.1, 300 sec: 2867.2). Total num frames: 200704. Throughput: 0: 929.5. Samples: 50536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:58:24,835][00595] Avg episode reward: [(0, '4.599')] +[2023-02-26 11:58:25,812][10654] Updated weights for policy 0, policy_version 50 (0.0011) +[2023-02-26 11:58:29,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 2949.1). Total num frames: 221184. Throughput: 0: 949.1. Samples: 53718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 11:58:29,839][00595] Avg episode reward: [(0, '4.501')] +[2023-02-26 11:58:34,582][10654] Updated weights for policy 0, policy_version 60 (0.0016) +[2023-02-26 11:58:34,832][00595] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3072.0). Total num frames: 245760. Throughput: 0: 980.3. Samples: 60806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:34,840][00595] Avg episode reward: [(0, '4.393')] +[2023-02-26 11:58:39,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3084.1). Total num frames: 262144. Throughput: 0: 934.2. Samples: 65958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:39,837][00595] Avg episode reward: [(0, '4.387')] +[2023-02-26 11:58:44,833][00595] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3049.2). Total num frames: 274432. Throughput: 0: 921.3. Samples: 68208. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:44,837][00595] Avg episode reward: [(0, '4.390')] +[2023-02-26 11:58:44,847][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth... +[2023-02-26 11:58:46,956][10654] Updated weights for policy 0, policy_version 70 (0.0025) +[2023-02-26 11:58:49,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3147.5). Total num frames: 299008. Throughput: 0: 954.4. Samples: 74162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:58:49,835][00595] Avg episode reward: [(0, '4.524')] +[2023-02-26 11:58:54,833][00595] Fps is (10 sec: 4915.0, 60 sec: 3822.9, 300 sec: 3235.8). Total num frames: 323584. Throughput: 0: 986.4. Samples: 81362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 11:58:54,840][00595] Avg episode reward: [(0, '4.407')] +[2023-02-26 11:58:55,697][10654] Updated weights for policy 0, policy_version 80 (0.0012) +[2023-02-26 11:58:59,837][00595] Fps is (10 sec: 3684.6, 60 sec: 3754.5, 300 sec: 3198.6). Total num frames: 335872. Throughput: 0: 961.4. Samples: 83776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 11:58:59,840][00595] Avg episode reward: [(0, '4.250')] +[2023-02-26 11:59:04,832][00595] Fps is (10 sec: 2867.4, 60 sec: 3822.9, 300 sec: 3202.3). Total num frames: 352256. Throughput: 0: 932.4. Samples: 88120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:59:04,834][00595] Avg episode reward: [(0, '4.383')] +[2023-02-26 11:59:07,808][10654] Updated weights for policy 0, policy_version 90 (0.0013) +[2023-02-26 11:59:09,832][00595] Fps is (10 sec: 4098.0, 60 sec: 3891.2, 300 sec: 3276.8). Total num frames: 376832. Throughput: 0: 981.7. Samples: 94710. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 11:59:09,837][00595] Avg episode reward: [(0, '4.461')] +[2023-02-26 11:59:14,832][00595] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3345.1). Total num frames: 401408. Throughput: 0: 989.8. Samples: 98258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 11:59:14,835][00595] Avg episode reward: [(0, '4.582')] +[2023-02-26 11:59:17,534][10654] Updated weights for policy 0, policy_version 100 (0.0021) +[2023-02-26 11:59:19,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3309.6). Total num frames: 413696. Throughput: 0: 955.8. Samples: 103818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:59:19,838][00595] Avg episode reward: [(0, '4.579')] +[2023-02-26 11:59:24,832][00595] Fps is (10 sec: 2867.2, 60 sec: 3823.0, 300 sec: 3308.3). Total num frames: 430080. Throughput: 0: 942.4. Samples: 108368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 11:59:24,835][00595] Avg episode reward: [(0, '4.611')] +[2023-02-26 11:59:24,842][10641] Saving new best policy, reward=4.611! +[2023-02-26 11:59:28,466][10654] Updated weights for policy 0, policy_version 110 (0.0015) +[2023-02-26 11:59:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3367.8). Total num frames: 454656. Throughput: 0: 972.4. Samples: 111964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:29,835][00595] Avg episode reward: [(0, '4.546')] +[2023-02-26 11:59:34,832][00595] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3423.1). Total num frames: 479232. Throughput: 0: 998.9. Samples: 119114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 11:59:34,838][00595] Avg episode reward: [(0, '4.524')] +[2023-02-26 11:59:38,721][10654] Updated weights for policy 0, policy_version 120 (0.0014) +[2023-02-26 11:59:39,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3389.8). Total num frames: 491520. Throughput: 0: 947.0. Samples: 123978. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:39,835][00595] Avg episode reward: [(0, '4.591')] +[2023-02-26 11:59:44,833][00595] Fps is (10 sec: 2457.5, 60 sec: 3822.9, 300 sec: 3358.7). Total num frames: 503808. Throughput: 0: 919.6. Samples: 125152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:44,840][00595] Avg episode reward: [(0, '4.378')] +[2023-02-26 11:59:49,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3408.9). Total num frames: 528384. Throughput: 0: 960.0. Samples: 131318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:49,840][00595] Avg episode reward: [(0, '4.627')] +[2023-02-26 11:59:49,843][10641] Saving new best policy, reward=4.627! +[2023-02-26 11:59:50,572][10654] Updated weights for policy 0, policy_version 130 (0.0017) +[2023-02-26 11:59:54,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3430.4). Total num frames: 548864. Throughput: 0: 965.8. Samples: 138170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:54,835][00595] Avg episode reward: [(0, '4.616')] +[2023-02-26 11:59:59,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3823.2, 300 sec: 3425.7). Total num frames: 565248. Throughput: 0: 933.8. Samples: 140280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 11:59:59,835][00595] Avg episode reward: [(0, '4.432')] +[2023-02-26 12:00:02,435][10654] Updated weights for policy 0, policy_version 140 (0.0021) +[2023-02-26 12:00:04,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3421.4). Total num frames: 581632. Throughput: 0: 910.8. Samples: 144806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:00:04,839][00595] Avg episode reward: [(0, '4.541')] +[2023-02-26 12:00:09,833][00595] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3464.0). Total num frames: 606208. Throughput: 0: 968.5. Samples: 151952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:00:09,838][00595] Avg episode reward: [(0, '4.582')] +[2023-02-26 12:00:11,345][10654] Updated weights for policy 0, policy_version 150 (0.0014) +[2023-02-26 12:00:14,837][00595] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3481.6). Total num frames: 626688. Throughput: 0: 967.6. Samples: 155504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:00:14,846][00595] Avg episode reward: [(0, '4.470')] +[2023-02-26 12:00:19,832][00595] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3476.1). Total num frames: 643072. Throughput: 0: 922.5. Samples: 160626. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:00:19,834][00595] Avg episode reward: [(0, '4.521')] +[2023-02-26 12:00:23,192][10654] Updated weights for policy 0, policy_version 160 (0.0021) +[2023-02-26 12:00:24,833][00595] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3470.8). Total num frames: 659456. Throughput: 0: 929.7. Samples: 165816. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:00:24,842][00595] Avg episode reward: [(0, '4.740')] +[2023-02-26 12:00:24,854][10641] Saving new best policy, reward=4.740! +[2023-02-26 12:00:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3507.9). Total num frames: 684032. Throughput: 0: 981.1. Samples: 169300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:00:29,834][00595] Avg episode reward: [(0, '4.446')] +[2023-02-26 12:00:32,032][10654] Updated weights for policy 0, policy_version 170 (0.0013) +[2023-02-26 12:00:34,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3522.6). Total num frames: 704512. Throughput: 0: 1000.4. Samples: 176336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:00:34,836][00595] Avg episode reward: [(0, '4.373')] +[2023-02-26 12:00:39,838][00595] Fps is (10 sec: 3684.4, 60 sec: 3822.6, 300 sec: 3516.5). Total num frames: 720896. Throughput: 0: 948.0. Samples: 180834. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-26 12:00:39,840][00595] Avg episode reward: [(0, '4.583')] +[2023-02-26 12:00:43,897][10654] Updated weights for policy 0, policy_version 180 (0.0028) +[2023-02-26 12:00:44,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3530.4). Total num frames: 741376. Throughput: 0: 954.8. Samples: 183248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:00:44,840][00595] Avg episode reward: [(0, '4.676')] +[2023-02-26 12:00:44,852][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000181_741376.pth... +[2023-02-26 12:00:49,832][00595] Fps is (10 sec: 4098.2, 60 sec: 3891.2, 300 sec: 3543.5). Total num frames: 761856. Throughput: 0: 1009.7. Samples: 190244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:00:49,841][00595] Avg episode reward: [(0, '4.694')] +[2023-02-26 12:00:52,569][10654] Updated weights for policy 0, policy_version 190 (0.0011) +[2023-02-26 12:00:54,836][00595] Fps is (10 sec: 4094.5, 60 sec: 3891.0, 300 sec: 3556.0). Total num frames: 782336. Throughput: 0: 995.7. Samples: 196762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:00:54,839][00595] Avg episode reward: [(0, '4.720')] +[2023-02-26 12:00:59,837][00595] Fps is (10 sec: 3684.8, 60 sec: 3890.9, 300 sec: 3549.8). Total num frames: 798720. Throughput: 0: 969.2. Samples: 199122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:00:59,840][00595] Avg episode reward: [(0, '4.760')] +[2023-02-26 12:00:59,846][10641] Saving new best policy, reward=4.760! +[2023-02-26 12:01:04,615][10654] Updated weights for policy 0, policy_version 200 (0.0035) +[2023-02-26 12:01:04,832][00595] Fps is (10 sec: 3687.7, 60 sec: 3959.5, 300 sec: 3561.7). Total num frames: 819200. Throughput: 0: 963.9. Samples: 204000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:01:04,838][00595] Avg episode reward: [(0, '4.690')] +[2023-02-26 12:01:09,832][00595] Fps is (10 sec: 4507.6, 60 sec: 3959.5, 300 sec: 3590.5). Total num frames: 843776. Throughput: 0: 1008.9. Samples: 211216. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:01:09,834][00595] Avg episode reward: [(0, '4.579')] +[2023-02-26 12:01:13,419][10654] Updated weights for policy 0, policy_version 210 (0.0014) +[2023-02-26 12:01:14,834][00595] Fps is (10 sec: 4505.1, 60 sec: 3959.4, 300 sec: 3601.1). Total num frames: 864256. Throughput: 0: 1009.3. Samples: 214722. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:01:14,836][00595] Avg episode reward: [(0, '4.833')] +[2023-02-26 12:01:14,854][10641] Saving new best policy, reward=4.833! +[2023-02-26 12:01:19,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3577.7). Total num frames: 876544. Throughput: 0: 954.3. Samples: 219280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:01:19,834][00595] Avg episode reward: [(0, '4.885')] +[2023-02-26 12:01:19,837][10641] Saving new best policy, reward=4.885! +[2023-02-26 12:01:24,832][00595] Fps is (10 sec: 3277.2, 60 sec: 3959.5, 300 sec: 3588.1). Total num frames: 897024. Throughput: 0: 977.1. Samples: 224796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:01:24,835][00595] Avg episode reward: [(0, '4.909')] +[2023-02-26 12:01:24,851][10641] Saving new best policy, reward=4.909! +[2023-02-26 12:01:25,507][10654] Updated weights for policy 0, policy_version 220 (0.0020) +[2023-02-26 12:01:29,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3614.1). Total num frames: 921600. Throughput: 0: 999.6. Samples: 228230. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:01:29,835][00595] Avg episode reward: [(0, '4.758')] +[2023-02-26 12:01:34,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3607.6). Total num frames: 937984. Throughput: 0: 993.8. Samples: 234964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:01:34,835][00595] Avg episode reward: [(0, '4.896')] +[2023-02-26 12:01:34,913][10654] Updated weights for policy 0, policy_version 230 (0.0011) +[2023-02-26 12:01:39,834][00595] Fps is (10 sec: 3276.3, 60 sec: 3891.5, 300 sec: 3601.4). Total num frames: 954368. Throughput: 0: 948.9. Samples: 239462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:01:39,838][00595] Avg episode reward: [(0, '4.866')] +[2023-02-26 12:01:44,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3610.5). Total num frames: 974848. Throughput: 0: 954.4. Samples: 242066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:01:44,839][00595] Avg episode reward: [(0, '4.932')] +[2023-02-26 12:01:44,851][10641] Saving new best policy, reward=4.932! +[2023-02-26 12:01:46,134][10654] Updated weights for policy 0, policy_version 240 (0.0017) +[2023-02-26 12:01:49,835][00595] Fps is (10 sec: 4504.9, 60 sec: 3959.3, 300 sec: 3634.2). Total num frames: 999424. Throughput: 0: 1005.3. Samples: 249242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:01:49,838][00595] Avg episode reward: [(0, '4.894')] +[2023-02-26 12:01:54,834][00595] Fps is (10 sec: 4505.6, 60 sec: 3959.7, 300 sec: 3642.5). Total num frames: 1019904. Throughput: 0: 982.0. Samples: 255408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:01:54,839][00595] Avg episode reward: [(0, '4.944')] +[2023-02-26 12:01:54,854][10641] Saving new best policy, reward=4.944! +[2023-02-26 12:01:56,051][10654] Updated weights for policy 0, policy_version 250 (0.0014) +[2023-02-26 12:01:59,832][00595] Fps is (10 sec: 3277.7, 60 sec: 3891.5, 300 sec: 3621.7). Total num frames: 1032192. Throughput: 0: 951.5. Samples: 257538. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:01:59,836][00595] Avg episode reward: [(0, '5.014')] +[2023-02-26 12:01:59,843][10641] Saving new best policy, reward=5.014! +[2023-02-26 12:02:04,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3629.9). Total num frames: 1052672. Throughput: 0: 970.4. Samples: 262948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:02:04,835][00595] Avg episode reward: [(0, '4.710')] +[2023-02-26 12:02:06,809][10654] Updated weights for policy 0, policy_version 260 (0.0031) +[2023-02-26 12:02:09,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 1077248. Throughput: 0: 1005.9. Samples: 270060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:02:09,839][00595] Avg episode reward: [(0, '4.844')] +[2023-02-26 12:02:14,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3707.2). Total num frames: 1093632. Throughput: 0: 996.6. Samples: 273078. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-26 12:02:14,841][00595] Avg episode reward: [(0, '4.938')] +[2023-02-26 12:02:17,985][10654] Updated weights for policy 0, policy_version 270 (0.0011) +[2023-02-26 12:02:19,832][00595] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1110016. Throughput: 0: 946.4. Samples: 277552. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-26 12:02:19,839][00595] Avg episode reward: [(0, '4.837')] +[2023-02-26 12:02:24,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1130496. Throughput: 0: 980.7. Samples: 283594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:02:24,840][00595] Avg episode reward: [(0, '4.647')] +[2023-02-26 12:02:27,738][10654] Updated weights for policy 0, policy_version 280 (0.0014) +[2023-02-26 12:02:29,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1155072. Throughput: 0: 1002.4. Samples: 287172. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:02:29,835][00595] Avg episode reward: [(0, '4.590')] +[2023-02-26 12:02:34,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1171456. Throughput: 0: 978.0. Samples: 293248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:02:34,839][00595] Avg episode reward: [(0, '4.734')] +[2023-02-26 12:02:39,432][10654] Updated weights for policy 0, policy_version 290 (0.0011) +[2023-02-26 12:02:39,832][00595] Fps is (10 sec: 3276.7, 60 sec: 3891.3, 300 sec: 3873.8). Total num frames: 1187840. Throughput: 0: 938.4. Samples: 297638. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:02:39,836][00595] Avg episode reward: [(0, '4.974')] +[2023-02-26 12:02:44,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1208320. Throughput: 0: 957.6. Samples: 300628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:02:44,835][00595] Avg episode reward: [(0, '5.177')] +[2023-02-26 12:02:44,845][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000295_1208320.pth... +[2023-02-26 12:02:44,955][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth +[2023-02-26 12:02:44,964][10641] Saving new best policy, reward=5.177! +[2023-02-26 12:02:48,679][10654] Updated weights for policy 0, policy_version 300 (0.0019) +[2023-02-26 12:02:49,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3891.4, 300 sec: 3860.0). Total num frames: 1232896. Throughput: 0: 994.8. Samples: 307714. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:02:49,834][00595] Avg episode reward: [(0, '4.818')] +[2023-02-26 12:02:54,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1249280. Throughput: 0: 955.8. Samples: 313070. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:02:54,838][00595] Avg episode reward: [(0, '4.692')] +[2023-02-26 12:02:59,833][00595] Fps is (10 sec: 3276.6, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1265664. Throughput: 0: 938.4. Samples: 315308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:02:59,841][00595] Avg episode reward: [(0, '4.771')] +[2023-02-26 12:03:00,745][10654] Updated weights for policy 0, policy_version 310 (0.0022) +[2023-02-26 12:03:04,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1286144. Throughput: 0: 968.5. Samples: 321134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:03:04,840][00595] Avg episode reward: [(0, '5.199')] +[2023-02-26 12:03:04,851][10641] Saving new best policy, reward=5.199! +[2023-02-26 12:03:09,502][10654] Updated weights for policy 0, policy_version 320 (0.0021) +[2023-02-26 12:03:09,832][00595] Fps is (10 sec: 4505.8, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1310720. Throughput: 0: 989.3. Samples: 328114. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:03:09,834][00595] Avg episode reward: [(0, '5.229')] +[2023-02-26 12:03:09,840][10641] Saving new best policy, reward=5.229! +[2023-02-26 12:03:14,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1327104. Throughput: 0: 967.0. Samples: 330686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:03:14,837][00595] Avg episode reward: [(0, '5.386')] +[2023-02-26 12:03:14,850][10641] Saving new best policy, reward=5.386! +[2023-02-26 12:03:19,833][00595] Fps is (10 sec: 2867.1, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1339392. Throughput: 0: 929.6. Samples: 335082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:03:19,838][00595] Avg episode reward: [(0, '5.366')] +[2023-02-26 12:03:21,932][10654] Updated weights for policy 0, policy_version 330 (0.0012) +[2023-02-26 12:03:24,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1363968. Throughput: 0: 975.4. Samples: 341532. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:03:24,838][00595] Avg episode reward: [(0, '5.305')] +[2023-02-26 12:03:29,832][00595] Fps is (10 sec: 4915.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1388544. Throughput: 0: 986.1. Samples: 345004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:03:29,835][00595] Avg episode reward: [(0, '5.229')] +[2023-02-26 12:03:30,734][10654] Updated weights for policy 0, policy_version 340 (0.0020) +[2023-02-26 12:03:34,834][00595] Fps is (10 sec: 4095.2, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 1404928. Throughput: 0: 954.8. Samples: 350684. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:03:34,837][00595] Avg episode reward: [(0, '5.091')] +[2023-02-26 12:03:39,832][00595] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1417216. Throughput: 0: 937.9. Samples: 355274. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:03:39,837][00595] Avg episode reward: [(0, '5.066')] +[2023-02-26 12:03:42,900][10654] Updated weights for policy 0, policy_version 350 (0.0035) +[2023-02-26 12:03:44,832][00595] Fps is (10 sec: 3687.1, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1441792. Throughput: 0: 957.5. Samples: 358394. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:03:44,835][00595] Avg episode reward: [(0, '5.293')] +[2023-02-26 12:03:49,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1462272. Throughput: 0: 986.7. Samples: 365536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:03:49,835][00595] Avg episode reward: [(0, '5.380')] +[2023-02-26 12:03:52,449][10654] Updated weights for policy 0, policy_version 360 (0.0014) +[2023-02-26 12:03:54,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 1478656. Throughput: 0: 946.3. Samples: 370696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:03:54,838][00595] Avg episode reward: [(0, '5.314')] +[2023-02-26 12:03:59,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3873.8). Total num frames: 1495040. Throughput: 0: 939.2. Samples: 372948. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:03:59,840][00595] Avg episode reward: [(0, '5.293')] +[2023-02-26 12:04:03,962][10654] Updated weights for policy 0, policy_version 370 (0.0012) +[2023-02-26 12:04:04,835][00595] Fps is (10 sec: 3685.4, 60 sec: 3822.8, 300 sec: 3859.9). Total num frames: 1515520. Throughput: 0: 976.8. Samples: 379040. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:04:04,838][00595] Avg episode reward: [(0, '5.463')] +[2023-02-26 12:04:04,849][10641] Saving new best policy, reward=5.463! +[2023-02-26 12:04:09,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1540096. Throughput: 0: 988.9. Samples: 386034. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:04:09,836][00595] Avg episode reward: [(0, '5.480')] +[2023-02-26 12:04:09,843][10641] Saving new best policy, reward=5.480! +[2023-02-26 12:04:13,992][10654] Updated weights for policy 0, policy_version 380 (0.0016) +[2023-02-26 12:04:14,835][00595] Fps is (10 sec: 4096.1, 60 sec: 3822.8, 300 sec: 3873.8). Total num frames: 1556480. Throughput: 0: 965.9. Samples: 388474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:04:14,837][00595] Avg episode reward: [(0, '5.423')] +[2023-02-26 12:04:19,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1572864. Throughput: 0: 938.2. Samples: 392900. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:04:19,839][00595] Avg episode reward: [(0, '5.291')] +[2023-02-26 12:04:24,719][10654] Updated weights for policy 0, policy_version 390 (0.0014) +[2023-02-26 12:04:24,832][00595] Fps is (10 sec: 4097.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1597440. Throughput: 0: 984.8. Samples: 399590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:04:24,835][00595] Avg episode reward: [(0, '5.199')] +[2023-02-26 12:04:29,835][00595] Fps is (10 sec: 4504.9, 60 sec: 3822.8, 300 sec: 3859.9). Total num frames: 1617920. Throughput: 0: 992.8. Samples: 403070. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:04:29,841][00595] Avg episode reward: [(0, '5.438')] +[2023-02-26 12:04:34,833][00595] Fps is (10 sec: 3686.0, 60 sec: 3823.0, 300 sec: 3873.8). Total num frames: 1634304. Throughput: 0: 953.5. Samples: 408444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:04:34,838][00595] Avg episode reward: [(0, '5.601')] +[2023-02-26 12:04:34,857][10641] Saving new best policy, reward=5.601! +[2023-02-26 12:04:35,969][10654] Updated weights for policy 0, policy_version 400 (0.0019) +[2023-02-26 12:04:39,832][00595] Fps is (10 sec: 3277.3, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 1650688. Throughput: 0: 939.7. Samples: 412982. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:04:39,834][00595] Avg episode reward: [(0, '5.900')] +[2023-02-26 12:04:39,838][10641] Saving new best policy, reward=5.900! +[2023-02-26 12:04:44,832][00595] Fps is (10 sec: 3686.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1671168. Throughput: 0: 964.3. Samples: 416342. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:04:44,835][00595] Avg episode reward: [(0, '6.149')] +[2023-02-26 12:04:44,903][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth... +[2023-02-26 12:04:45,024][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000181_741376.pth +[2023-02-26 12:04:45,040][10641] Saving new best policy, reward=6.149! +[2023-02-26 12:04:45,910][10654] Updated weights for policy 0, policy_version 410 (0.0028) +[2023-02-26 12:04:49,834][00595] Fps is (10 sec: 4504.8, 60 sec: 3891.1, 300 sec: 3887.7). Total num frames: 1695744. Throughput: 0: 986.1. Samples: 423414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:04:49,837][00595] Avg episode reward: [(0, '6.048')] +[2023-02-26 12:04:54,840][00595] Fps is (10 sec: 4092.8, 60 sec: 3890.7, 300 sec: 3887.6). Total num frames: 1712128. Throughput: 0: 942.2. Samples: 428440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:04:54,842][00595] Avg episode reward: [(0, '5.788')] +[2023-02-26 12:04:57,518][10654] Updated weights for policy 0, policy_version 420 (0.0020) +[2023-02-26 12:04:59,833][00595] Fps is (10 sec: 2867.6, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1724416. Throughput: 0: 936.6. Samples: 430620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:04:59,839][00595] Avg episode reward: [(0, '5.994')] +[2023-02-26 12:05:04,832][00595] Fps is (10 sec: 3689.3, 60 sec: 3891.4, 300 sec: 3873.8). Total num frames: 1748992. Throughput: 0: 974.8. Samples: 436764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:05:04,834][00595] Avg episode reward: [(0, '5.941')] +[2023-02-26 12:05:06,962][10654] Updated weights for policy 0, policy_version 430 (0.0040) +[2023-02-26 12:05:09,836][00595] Fps is (10 sec: 4913.7, 60 sec: 3891.0, 300 sec: 3887.7). Total num frames: 1773568. Throughput: 0: 985.7. Samples: 443952. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:05:09,841][00595] Avg episode reward: [(0, '5.818')] +[2023-02-26 12:05:14,837][00595] Fps is (10 sec: 3684.8, 60 sec: 3822.8, 300 sec: 3873.8). Total num frames: 1785856. Throughput: 0: 957.1. Samples: 446142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:05:14,845][00595] Avg episode reward: [(0, '5.866')] +[2023-02-26 12:05:19,286][10654] Updated weights for policy 0, policy_version 440 (0.0025) +[2023-02-26 12:05:19,832][00595] Fps is (10 sec: 2868.1, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1802240. Throughput: 0: 934.3. Samples: 450488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:05:19,840][00595] Avg episode reward: [(0, '6.108')] +[2023-02-26 12:05:24,832][00595] Fps is (10 sec: 4097.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1826816. Throughput: 0: 986.8. Samples: 457388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:05:24,835][00595] Avg episode reward: [(0, '6.047')] +[2023-02-26 12:05:27,825][10654] Updated weights for policy 0, policy_version 450 (0.0012) +[2023-02-26 12:05:29,833][00595] Fps is (10 sec: 4915.1, 60 sec: 3891.3, 300 sec: 3887.7). Total num frames: 1851392. Throughput: 0: 992.6. Samples: 461010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:05:29,837][00595] Avg episode reward: [(0, '6.246')] +[2023-02-26 12:05:29,840][10641] Saving new best policy, reward=6.246! +[2023-02-26 12:05:34,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3873.9). Total num frames: 1863680. Throughput: 0: 950.5. Samples: 466186. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:05:34,849][00595] Avg episode reward: [(0, '6.047')] +[2023-02-26 12:05:39,832][00595] Fps is (10 sec: 2867.3, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1880064. Throughput: 0: 945.9. Samples: 470998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:05:39,839][00595] Avg episode reward: [(0, '6.242')] +[2023-02-26 12:05:40,106][10654] Updated weights for policy 0, policy_version 460 (0.0015) +[2023-02-26 12:05:44,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1904640. Throughput: 0: 977.7. Samples: 474618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:05:44,839][00595] Avg episode reward: [(0, '6.314')] +[2023-02-26 12:05:44,856][10641] Saving new best policy, reward=6.314! +[2023-02-26 12:05:48,826][10654] Updated weights for policy 0, policy_version 470 (0.0022) +[2023-02-26 12:05:49,835][00595] Fps is (10 sec: 4504.5, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 1925120. Throughput: 0: 995.3. Samples: 481554. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-26 12:05:49,843][00595] Avg episode reward: [(0, '5.908')] +[2023-02-26 12:05:54,834][00595] Fps is (10 sec: 3685.7, 60 sec: 3823.3, 300 sec: 3873.9). Total num frames: 1941504. Throughput: 0: 942.5. Samples: 486364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:05:54,839][00595] Avg episode reward: [(0, '6.196')] +[2023-02-26 12:05:59,832][00595] Fps is (10 sec: 3277.6, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1957888. Throughput: 0: 946.7. Samples: 488738. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:05:59,840][00595] Avg episode reward: [(0, '6.269')] +[2023-02-26 12:06:00,778][10654] Updated weights for policy 0, policy_version 480 (0.0020) +[2023-02-26 12:06:04,832][00595] Fps is (10 sec: 4096.8, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1982464. Throughput: 0: 998.8. Samples: 495436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:06:04,834][00595] Avg episode reward: [(0, '6.463')] +[2023-02-26 12:06:04,854][10641] Saving new best policy, reward=6.463! +[2023-02-26 12:06:09,662][10654] Updated weights for policy 0, policy_version 490 (0.0021) +[2023-02-26 12:06:09,832][00595] Fps is (10 sec: 4915.2, 60 sec: 3891.4, 300 sec: 3873.9). Total num frames: 2007040. Throughput: 0: 996.9. Samples: 502248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:06:09,838][00595] Avg episode reward: [(0, '6.518')] +[2023-02-26 12:06:09,850][10641] Saving new best policy, reward=6.518! +[2023-02-26 12:06:14,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.5, 300 sec: 3873.8). Total num frames: 2019328. Throughput: 0: 965.7. Samples: 504466. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:06:14,843][00595] Avg episode reward: [(0, '7.092')] +[2023-02-26 12:06:14,853][10641] Saving new best policy, reward=7.092! +[2023-02-26 12:06:19,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2039808. Throughput: 0: 950.7. Samples: 508966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:06:19,835][00595] Avg episode reward: [(0, '7.149')] +[2023-02-26 12:06:19,837][10641] Saving new best policy, reward=7.149! +[2023-02-26 12:06:21,537][10654] Updated weights for policy 0, policy_version 500 (0.0011) +[2023-02-26 12:06:24,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2060288. Throughput: 0: 1000.0. Samples: 515996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:06:24,835][00595] Avg episode reward: [(0, '6.885')] +[2023-02-26 12:06:29,833][00595] Fps is (10 sec: 4095.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 2080768. Throughput: 0: 997.4. Samples: 519500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:06:29,838][00595] Avg episode reward: [(0, '6.747')] +[2023-02-26 12:06:31,178][10654] Updated weights for policy 0, policy_version 510 (0.0013) +[2023-02-26 12:06:34,833][00595] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3873.9). Total num frames: 2097152. Throughput: 0: 955.8. Samples: 524562. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:06:34,834][00595] Avg episode reward: [(0, '6.665')] +[2023-02-26 12:06:39,832][00595] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2117632. Throughput: 0: 961.3. Samples: 529620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:06:39,835][00595] Avg episode reward: [(0, '6.504')] +[2023-02-26 12:06:42,530][10654] Updated weights for policy 0, policy_version 520 (0.0021) +[2023-02-26 12:06:44,832][00595] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2138112. Throughput: 0: 986.0. Samples: 533108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:06:44,835][00595] Avg episode reward: [(0, '6.733')] +[2023-02-26 12:06:44,846][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000522_2138112.pth... +[2023-02-26 12:06:44,965][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000295_1208320.pth +[2023-02-26 12:06:49,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.4, 300 sec: 3860.0). Total num frames: 2158592. Throughput: 0: 988.0. Samples: 539898. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:06:49,836][00595] Avg episode reward: [(0, '6.345')] +[2023-02-26 12:06:52,888][10654] Updated weights for policy 0, policy_version 530 (0.0014) +[2023-02-26 12:06:54,836][00595] Fps is (10 sec: 3685.2, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 2174976. Throughput: 0: 936.2. Samples: 544380. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:06:54,842][00595] Avg episode reward: [(0, '6.400')] +[2023-02-26 12:06:59,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2191360. Throughput: 0: 938.2. Samples: 546686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:06:59,835][00595] Avg episode reward: [(0, '6.534')] +[2023-02-26 12:07:03,254][10654] Updated weights for policy 0, policy_version 540 (0.0021) +[2023-02-26 12:07:04,834][00595] Fps is (10 sec: 4096.7, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 2215936. Throughput: 0: 994.1. Samples: 553702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:07:04,836][00595] Avg episode reward: [(0, '6.399')] +[2023-02-26 12:07:09,832][00595] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 2236416. Throughput: 0: 982.9. Samples: 560226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:07:09,835][00595] Avg episode reward: [(0, '6.316')] +[2023-02-26 12:07:14,237][10654] Updated weights for policy 0, policy_version 550 (0.0021) +[2023-02-26 12:07:14,832][00595] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2252800. Throughput: 0: 954.7. Samples: 562460. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:07:14,838][00595] Avg episode reward: [(0, '6.659')] +[2023-02-26 12:07:19,832][00595] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2269184. Throughput: 0: 949.0. Samples: 567266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:07:19,840][00595] Avg episode reward: [(0, '7.091')] +[2023-02-26 12:07:24,015][10654] Updated weights for policy 0, policy_version 560 (0.0026) +[2023-02-26 12:07:24,834][00595] Fps is (10 sec: 4095.5, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 2293760. Throughput: 0: 997.1. Samples: 574492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:07:24,840][00595] Avg episode reward: [(0, '7.580')] +[2023-02-26 12:07:24,897][10641] Saving new best policy, reward=7.580! +[2023-02-26 12:07:29,833][00595] Fps is (10 sec: 4505.2, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2314240. Throughput: 0: 1000.2. Samples: 578116. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:07:29,841][00595] Avg episode reward: [(0, '7.819')] +[2023-02-26 12:07:29,844][10641] Saving new best policy, reward=7.819! +[2023-02-26 12:07:34,832][00595] Fps is (10 sec: 3686.9, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2330624. Throughput: 0: 947.5. Samples: 582536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:07:34,836][00595] Avg episode reward: [(0, '8.209')] +[2023-02-26 12:07:34,848][10641] Saving new best policy, reward=8.209! +[2023-02-26 12:07:35,732][10654] Updated weights for policy 0, policy_version 570 (0.0016) +[2023-02-26 12:07:39,832][00595] Fps is (10 sec: 3686.7, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2351104. Throughput: 0: 971.7. Samples: 588102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:07:39,835][00595] Avg episode reward: [(0, '7.738')] +[2023-02-26 12:07:44,724][10654] Updated weights for policy 0, policy_version 580 (0.0018) +[2023-02-26 12:07:44,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2375680. Throughput: 0: 1000.3. Samples: 591700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:07:44,840][00595] Avg episode reward: [(0, '7.319')] +[2023-02-26 12:07:49,834][00595] Fps is (10 sec: 4095.4, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 2392064. Throughput: 0: 993.2. Samples: 598398. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:07:49,841][00595] Avg episode reward: [(0, '7.557')] +[2023-02-26 12:07:54,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.4, 300 sec: 3873.8). Total num frames: 2408448. Throughput: 0: 946.8. Samples: 602834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:07:54,836][00595] Avg episode reward: [(0, '7.289')] +[2023-02-26 12:07:56,799][10654] Updated weights for policy 0, policy_version 590 (0.0027) +[2023-02-26 12:07:59,832][00595] Fps is (10 sec: 3686.9, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2428928. Throughput: 0: 954.1. Samples: 605394. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:07:59,835][00595] Avg episode reward: [(0, '7.911')] +[2023-02-26 12:08:04,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3959.6, 300 sec: 3873.8). Total num frames: 2453504. Throughput: 0: 1005.8. Samples: 612526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:08:04,841][00595] Avg episode reward: [(0, '8.247')] +[2023-02-26 12:08:04,853][10641] Saving new best policy, reward=8.247! +[2023-02-26 12:08:05,694][10654] Updated weights for policy 0, policy_version 600 (0.0020) +[2023-02-26 12:08:09,836][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2469888. Throughput: 0: 975.0. Samples: 618364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:08:09,841][00595] Avg episode reward: [(0, '8.421')] +[2023-02-26 12:08:09,844][10641] Saving new best policy, reward=8.421! +[2023-02-26 12:08:14,833][00595] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2486272. Throughput: 0: 943.1. Samples: 620554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:08:14,844][00595] Avg episode reward: [(0, '8.719')] +[2023-02-26 12:08:14,862][10641] Saving new best policy, reward=8.719! +[2023-02-26 12:08:17,977][10654] Updated weights for policy 0, policy_version 610 (0.0032) +[2023-02-26 12:08:19,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2506752. Throughput: 0: 962.4. Samples: 625842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:08:19,838][00595] Avg episode reward: [(0, '9.217')] +[2023-02-26 12:08:19,844][10641] Saving new best policy, reward=9.217! +[2023-02-26 12:08:24,832][00595] Fps is (10 sec: 4096.1, 60 sec: 3891.3, 300 sec: 3860.0). Total num frames: 2527232. Throughput: 0: 999.0. Samples: 633056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:08:24,837][00595] Avg episode reward: [(0, '9.276')] +[2023-02-26 12:08:24,845][10641] Saving new best policy, reward=9.276! +[2023-02-26 12:08:26,716][10654] Updated weights for policy 0, policy_version 620 (0.0026) +[2023-02-26 12:08:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.9). Total num frames: 2547712. Throughput: 0: 989.0. Samples: 636206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:08:29,835][00595] Avg episode reward: [(0, '8.640')] +[2023-02-26 12:08:34,833][00595] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2564096. Throughput: 0: 943.0. Samples: 640834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:08:34,835][00595] Avg episode reward: [(0, '8.547')] +[2023-02-26 12:08:38,515][10654] Updated weights for policy 0, policy_version 630 (0.0012) +[2023-02-26 12:08:39,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2584576. Throughput: 0: 975.8. Samples: 646744. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:08:39,839][00595] Avg episode reward: [(0, '8.766')] +[2023-02-26 12:08:44,832][00595] Fps is (10 sec: 4505.8, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2609152. Throughput: 0: 997.2. Samples: 650270. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:08:44,836][00595] Avg episode reward: [(0, '9.726')] +[2023-02-26 12:08:44,849][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth... +[2023-02-26 12:08:44,956][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth +[2023-02-26 12:08:44,969][10641] Saving new best policy, reward=9.726! +[2023-02-26 12:08:47,873][10654] Updated weights for policy 0, policy_version 640 (0.0013) +[2023-02-26 12:08:49,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3887.7). Total num frames: 2625536. Throughput: 0: 973.9. Samples: 656350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:08:49,837][00595] Avg episode reward: [(0, '9.930')] +[2023-02-26 12:08:49,845][10641] Saving new best policy, reward=9.930! +[2023-02-26 12:08:54,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2641920. Throughput: 0: 942.6. Samples: 660780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:08:54,837][00595] Avg episode reward: [(0, '9.794')] +[2023-02-26 12:08:59,629][10654] Updated weights for policy 0, policy_version 650 (0.0017) +[2023-02-26 12:08:59,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 2662400. Throughput: 0: 957.0. Samples: 663620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-26 12:08:59,839][00595] Avg episode reward: [(0, '10.195')] +[2023-02-26 12:08:59,842][10641] Saving new best policy, reward=10.195! +[2023-02-26 12:09:04,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2686976. Throughput: 0: 1000.0. Samples: 670844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:09:04,834][00595] Avg episode reward: [(0, '10.030')] +[2023-02-26 12:09:09,403][10654] Updated weights for policy 0, policy_version 660 (0.0013) +[2023-02-26 12:09:09,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 2703360. Throughput: 0: 965.9. Samples: 676520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:09:09,839][00595] Avg episode reward: [(0, '10.134')] +[2023-02-26 12:09:14,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2719744. Throughput: 0: 946.3. Samples: 678790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:09:14,838][00595] Avg episode reward: [(0, '10.135')] +[2023-02-26 12:09:19,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2740224. Throughput: 0: 972.0. Samples: 684572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:09:19,840][00595] Avg episode reward: [(0, '9.681')] +[2023-02-26 12:09:20,286][10654] Updated weights for policy 0, policy_version 670 (0.0032) +[2023-02-26 12:09:24,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2764800. Throughput: 0: 1002.2. Samples: 691842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:09:24,837][00595] Avg episode reward: [(0, '9.373')] +[2023-02-26 12:09:29,836][00595] Fps is (10 sec: 4094.6, 60 sec: 3891.0, 300 sec: 3887.7). Total num frames: 2781184. Throughput: 0: 988.9. Samples: 694774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:09:29,838][00595] Avg episode reward: [(0, '9.223')] +[2023-02-26 12:09:30,187][10654] Updated weights for policy 0, policy_version 680 (0.0038) +[2023-02-26 12:09:34,833][00595] Fps is (10 sec: 3276.5, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2797568. Throughput: 0: 951.2. Samples: 699156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:09:34,838][00595] Avg episode reward: [(0, '9.756')] +[2023-02-26 12:09:39,832][00595] Fps is (10 sec: 3687.6, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2818048. Throughput: 0: 995.6. Samples: 705584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:09:39,839][00595] Avg episode reward: [(0, '10.223')] +[2023-02-26 12:09:39,842][10641] Saving new best policy, reward=10.223! +[2023-02-26 12:09:40,866][10654] Updated weights for policy 0, policy_version 690 (0.0024) +[2023-02-26 12:09:44,832][00595] Fps is (10 sec: 4506.0, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 2842624. Throughput: 0: 1011.5. Samples: 709138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:09:44,839][00595] Avg episode reward: [(0, '10.625')] +[2023-02-26 12:09:44,849][10641] Saving new best policy, reward=10.625! +[2023-02-26 12:09:49,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 2859008. Throughput: 0: 981.0. Samples: 714988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:09:49,836][00595] Avg episode reward: [(0, '10.897')] +[2023-02-26 12:09:49,843][10641] Saving new best policy, reward=10.897! +[2023-02-26 12:09:51,635][10654] Updated weights for policy 0, policy_version 700 (0.0012) +[2023-02-26 12:09:54,833][00595] Fps is (10 sec: 3276.5, 60 sec: 3891.1, 300 sec: 3901.6). Total num frames: 2875392. Throughput: 0: 956.2. Samples: 719550. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:09:54,837][00595] Avg episode reward: [(0, '10.842')] +[2023-02-26 12:09:59,832][00595] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2899968. Throughput: 0: 976.7. Samples: 722742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:09:59,835][00595] Avg episode reward: [(0, '11.877')] +[2023-02-26 12:09:59,837][10641] Saving new best policy, reward=11.877! +[2023-02-26 12:10:01,606][10654] Updated weights for policy 0, policy_version 710 (0.0022) +[2023-02-26 12:10:04,832][00595] Fps is (10 sec: 4506.1, 60 sec: 3891.2, 300 sec: 3887.8). Total num frames: 2920448. Throughput: 0: 1010.2. Samples: 730030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:10:04,834][00595] Avg episode reward: [(0, '11.034')] +[2023-02-26 12:10:09,837][00595] Fps is (10 sec: 4094.2, 60 sec: 3959.2, 300 sec: 3915.5). Total num frames: 2940928. Throughput: 0: 972.5. Samples: 735610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:10:09,838][00595] Avg episode reward: [(0, '12.270')] +[2023-02-26 12:10:09,848][10641] Saving new best policy, reward=12.270! +[2023-02-26 12:10:12,565][10654] Updated weights for policy 0, policy_version 720 (0.0017) +[2023-02-26 12:10:14,833][00595] Fps is (10 sec: 3276.5, 60 sec: 3891.1, 300 sec: 3901.6). Total num frames: 2953216. Throughput: 0: 958.0. Samples: 737882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:10:14,837][00595] Avg episode reward: [(0, '11.885')] +[2023-02-26 12:10:19,832][00595] Fps is (10 sec: 3688.0, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 2977792. Throughput: 0: 998.1. Samples: 744068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:10:19,840][00595] Avg episode reward: [(0, '12.556')] +[2023-02-26 12:10:19,843][10641] Saving new best policy, reward=12.556! +[2023-02-26 12:10:21,777][10654] Updated weights for policy 0, policy_version 730 (0.0022) +[2023-02-26 12:10:24,832][00595] Fps is (10 sec: 4915.6, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3002368. Throughput: 0: 1017.0. Samples: 751348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:10:24,839][00595] Avg episode reward: [(0, '12.811')] +[2023-02-26 12:10:24,852][10641] Saving new best policy, reward=12.811! +[2023-02-26 12:10:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3959.7, 300 sec: 3915.5). Total num frames: 3018752. Throughput: 0: 991.3. Samples: 753748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:10:29,837][00595] Avg episode reward: [(0, '13.455')] +[2023-02-26 12:10:29,845][10641] Saving new best policy, reward=13.455! +[2023-02-26 12:10:33,574][10654] Updated weights for policy 0, policy_version 740 (0.0029) +[2023-02-26 12:10:34,833][00595] Fps is (10 sec: 3276.7, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 3035136. Throughput: 0: 961.8. Samples: 758268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:10:34,840][00595] Avg episode reward: [(0, '14.245')] +[2023-02-26 12:10:34,856][10641] Saving new best policy, reward=14.245! +[2023-02-26 12:10:39,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 3055616. Throughput: 0: 1002.6. Samples: 764666. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:10:39,840][00595] Avg episode reward: [(0, '15.002')] +[2023-02-26 12:10:39,845][10641] Saving new best policy, reward=15.002! +[2023-02-26 12:10:42,968][10654] Updated weights for policy 0, policy_version 750 (0.0018) +[2023-02-26 12:10:44,833][00595] Fps is (10 sec: 4505.5, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 3080192. Throughput: 0: 1008.3. Samples: 768114. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:10:44,840][00595] Avg episode reward: [(0, '15.687')] +[2023-02-26 12:10:44,852][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000752_3080192.pth... +[2023-02-26 12:10:44,983][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000522_2138112.pth +[2023-02-26 12:10:45,004][10641] Saving new best policy, reward=15.687! +[2023-02-26 12:10:49,833][00595] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 3092480. Throughput: 0: 966.3. Samples: 773512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:10:49,841][00595] Avg episode reward: [(0, '15.035')] +[2023-02-26 12:10:54,833][00595] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 3108864. Throughput: 0: 937.8. Samples: 777808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:10:54,839][00595] Avg episode reward: [(0, '14.879')] +[2023-02-26 12:10:55,763][10654] Updated weights for policy 0, policy_version 760 (0.0021) +[2023-02-26 12:10:59,832][00595] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 3129344. Throughput: 0: 951.5. Samples: 780698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:10:59,835][00595] Avg episode reward: [(0, '14.336')] +[2023-02-26 12:11:04,770][10654] Updated weights for policy 0, policy_version 770 (0.0022) +[2023-02-26 12:11:04,832][00595] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 3153920. Throughput: 0: 965.8. Samples: 787528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:11:04,835][00595] Avg episode reward: [(0, '13.023')] +[2023-02-26 12:11:09,836][00595] Fps is (10 sec: 3685.1, 60 sec: 3754.7, 300 sec: 3887.7). Total num frames: 3166208. Throughput: 0: 919.0. Samples: 792708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:11:09,838][00595] Avg episode reward: [(0, '13.704')] +[2023-02-26 12:11:14,832][00595] Fps is (10 sec: 2457.6, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 3178496. Throughput: 0: 908.7. Samples: 794640. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:11:14,835][00595] Avg episode reward: [(0, '13.453')] +[2023-02-26 12:11:18,203][10654] Updated weights for policy 0, policy_version 780 (0.0037) +[2023-02-26 12:11:19,832][00595] Fps is (10 sec: 3277.9, 60 sec: 3686.4, 300 sec: 3860.0). Total num frames: 3198976. Throughput: 0: 918.5. Samples: 799602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:11:19,835][00595] Avg episode reward: [(0, '13.645')] +[2023-02-26 12:11:24,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3873.8). Total num frames: 3223552. Throughput: 0: 920.2. Samples: 806076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:11:24,840][00595] Avg episode reward: [(0, '14.513')] +[2023-02-26 12:11:28,349][10654] Updated weights for policy 0, policy_version 790 (0.0013) +[2023-02-26 12:11:29,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3860.0). Total num frames: 3235840. Throughput: 0: 903.9. Samples: 808788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:11:29,836][00595] Avg episode reward: [(0, '14.026')] +[2023-02-26 12:11:34,832][00595] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3846.1). Total num frames: 3252224. Throughput: 0: 877.3. Samples: 812990. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:11:34,835][00595] Avg episode reward: [(0, '13.914')] +[2023-02-26 12:11:39,833][00595] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3846.1). Total num frames: 3272704. Throughput: 0: 907.3. Samples: 818636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:11:39,835][00595] Avg episode reward: [(0, '15.128')] +[2023-02-26 12:11:40,560][10654] Updated weights for policy 0, policy_version 800 (0.0021) +[2023-02-26 12:11:44,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3846.1). Total num frames: 3293184. Throughput: 0: 916.4. Samples: 821934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:11:44,837][00595] Avg episode reward: [(0, '15.690')] +[2023-02-26 12:11:44,851][10641] Saving new best policy, reward=15.690! +[2023-02-26 12:11:49,832][00595] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3846.1). Total num frames: 3309568. Throughput: 0: 897.6. Samples: 827922. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:11:49,835][00595] Avg episode reward: [(0, '15.576')] +[2023-02-26 12:11:51,592][10654] Updated weights for policy 0, policy_version 810 (0.0026) +[2023-02-26 12:11:54,835][00595] Fps is (10 sec: 3276.0, 60 sec: 3618.0, 300 sec: 3846.0). Total num frames: 3325952. Throughput: 0: 872.9. Samples: 831986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:11:54,842][00595] Avg episode reward: [(0, '16.209')] +[2023-02-26 12:11:54,854][10641] Saving new best policy, reward=16.209! +[2023-02-26 12:11:59,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3818.3). Total num frames: 3342336. Throughput: 0: 879.9. Samples: 834234. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:11:59,843][00595] Avg episode reward: [(0, '16.362')] +[2023-02-26 12:11:59,847][10641] Saving new best policy, reward=16.362! +[2023-02-26 12:12:02,584][10654] Updated weights for policy 0, policy_version 820 (0.0022) +[2023-02-26 12:12:04,832][00595] Fps is (10 sec: 4097.0, 60 sec: 3549.9, 300 sec: 3832.2). Total num frames: 3366912. Throughput: 0: 926.1. Samples: 841276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:12:04,834][00595] Avg episode reward: [(0, '16.702')] +[2023-02-26 12:12:04,851][10641] Saving new best policy, reward=16.702! +[2023-02-26 12:12:09,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3686.6, 300 sec: 3846.1). Total num frames: 3387392. Throughput: 0: 919.7. Samples: 847462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:12:09,845][00595] Avg episode reward: [(0, '17.133')] +[2023-02-26 12:12:09,851][10641] Saving new best policy, reward=17.133! +[2023-02-26 12:12:13,790][10654] Updated weights for policy 0, policy_version 830 (0.0013) +[2023-02-26 12:12:14,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 3399680. Throughput: 0: 905.9. Samples: 849554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:12:14,842][00595] Avg episode reward: [(0, '17.658')] +[2023-02-26 12:12:14,863][10641] Saving new best policy, reward=17.658! +[2023-02-26 12:12:19,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3818.3). Total num frames: 3420160. Throughput: 0: 921.9. Samples: 854476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:12:19,836][00595] Avg episode reward: [(0, '18.195')] +[2023-02-26 12:12:19,841][10641] Saving new best policy, reward=18.195! +[2023-02-26 12:12:24,095][10654] Updated weights for policy 0, policy_version 840 (0.0028) +[2023-02-26 12:12:24,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3818.3). Total num frames: 3440640. Throughput: 0: 946.9. Samples: 861248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:12:24,840][00595] Avg episode reward: [(0, '18.127')] +[2023-02-26 12:12:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3461120. Throughput: 0: 946.4. Samples: 864522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:12:29,840][00595] Avg episode reward: [(0, '17.542')] +[2023-02-26 12:12:34,833][00595] Fps is (10 sec: 3686.0, 60 sec: 3754.6, 300 sec: 3818.3). Total num frames: 3477504. Throughput: 0: 910.7. Samples: 868904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:12:34,839][00595] Avg episode reward: [(0, '17.655')] +[2023-02-26 12:12:36,210][10654] Updated weights for policy 0, policy_version 850 (0.0021) +[2023-02-26 12:12:39,833][00595] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 3493888. Throughput: 0: 939.2. Samples: 874248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:12:39,841][00595] Avg episode reward: [(0, '17.812')] +[2023-02-26 12:12:44,832][00595] Fps is (10 sec: 4096.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 3518464. Throughput: 0: 969.8. Samples: 877876. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:12:44,840][00595] Avg episode reward: [(0, '17.562')] +[2023-02-26 12:12:44,853][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000859_3518464.pth... +[2023-02-26 12:12:44,977][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth +[2023-02-26 12:12:45,180][10654] Updated weights for policy 0, policy_version 860 (0.0036) +[2023-02-26 12:12:49,833][00595] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3538944. Throughput: 0: 962.0. Samples: 884568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:12:49,838][00595] Avg episode reward: [(0, '17.675')] +[2023-02-26 12:12:54,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3804.4). Total num frames: 3551232. Throughput: 0: 923.7. Samples: 889030. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:12:54,835][00595] Avg episode reward: [(0, '18.503')] +[2023-02-26 12:12:54,862][10641] Saving new best policy, reward=18.503! +[2023-02-26 12:12:57,693][10654] Updated weights for policy 0, policy_version 870 (0.0025) +[2023-02-26 12:12:59,832][00595] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3571712. Throughput: 0: 923.6. Samples: 891116. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:12:59,842][00595] Avg episode reward: [(0, '18.788')] +[2023-02-26 12:12:59,845][10641] Saving new best policy, reward=18.788! +[2023-02-26 12:13:04,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3592192. Throughput: 0: 958.4. Samples: 897604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:13:04,836][00595] Avg episode reward: [(0, '18.415')] +[2023-02-26 12:13:06,945][10654] Updated weights for policy 0, policy_version 880 (0.0013) +[2023-02-26 12:13:09,836][00595] Fps is (10 sec: 4094.6, 60 sec: 3754.5, 300 sec: 3818.3). Total num frames: 3612672. Throughput: 0: 944.3. Samples: 903744. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:13:09,838][00595] Avg episode reward: [(0, '19.338')] +[2023-02-26 12:13:09,845][10641] Saving new best policy, reward=19.338! +[2023-02-26 12:13:14,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3624960. Throughput: 0: 919.9. Samples: 905916. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-26 12:13:14,838][00595] Avg episode reward: [(0, '19.153')] +[2023-02-26 12:13:19,595][10654] Updated weights for policy 0, policy_version 890 (0.0016) +[2023-02-26 12:13:19,832][00595] Fps is (10 sec: 3277.9, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3645440. Throughput: 0: 927.8. Samples: 910654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:13:19,835][00595] Avg episode reward: [(0, '19.322')] +[2023-02-26 12:13:24,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3665920. Throughput: 0: 958.2. Samples: 917366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:13:24,834][00595] Avg episode reward: [(0, '19.345')] +[2023-02-26 12:13:24,848][10641] Saving new best policy, reward=19.345! +[2023-02-26 12:13:29,427][10654] Updated weights for policy 0, policy_version 900 (0.0013) +[2023-02-26 12:13:29,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3686400. Throughput: 0: 950.8. Samples: 920662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:13:29,836][00595] Avg episode reward: [(0, '19.669')] +[2023-02-26 12:13:29,841][10641] Saving new best policy, reward=19.669! +[2023-02-26 12:13:34,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3776.7). Total num frames: 3698688. Throughput: 0: 900.7. Samples: 925098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:13:34,839][00595] Avg episode reward: [(0, '18.411')] +[2023-02-26 12:13:39,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3719168. Throughput: 0: 914.6. Samples: 930186. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:13:39,835][00595] Avg episode reward: [(0, '18.517')] +[2023-02-26 12:13:41,550][10654] Updated weights for policy 0, policy_version 910 (0.0012) +[2023-02-26 12:13:44,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3776.6). Total num frames: 3739648. Throughput: 0: 940.6. Samples: 933442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:13:44,835][00595] Avg episode reward: [(0, '17.234')] +[2023-02-26 12:13:49,838][00595] Fps is (10 sec: 4093.7, 60 sec: 3686.1, 300 sec: 3790.5). Total num frames: 3760128. Throughput: 0: 931.8. Samples: 939540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:13:49,846][00595] Avg episode reward: [(0, '18.028')] +[2023-02-26 12:13:52,709][10654] Updated weights for policy 0, policy_version 920 (0.0024) +[2023-02-26 12:13:54,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 3772416. Throughput: 0: 891.1. Samples: 943840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:13:54,834][00595] Avg episode reward: [(0, '18.594')] +[2023-02-26 12:13:59,832][00595] Fps is (10 sec: 2868.8, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3788800. Throughput: 0: 890.2. Samples: 945974. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:13:59,841][00595] Avg episode reward: [(0, '19.715')] +[2023-02-26 12:13:59,846][10641] Saving new best policy, reward=19.715! +[2023-02-26 12:14:04,159][10654] Updated weights for policy 0, policy_version 930 (0.0029) +[2023-02-26 12:14:04,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3748.9). Total num frames: 3809280. Throughput: 0: 924.1. Samples: 952238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-26 12:14:04,842][00595] Avg episode reward: [(0, '19.771')] +[2023-02-26 12:14:04,858][10641] Saving new best policy, reward=19.771! +[2023-02-26 12:14:09,832][00595] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3762.8). Total num frames: 3829760. Throughput: 0: 909.2. Samples: 958278. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:14:09,837][00595] Avg episode reward: [(0, '21.821')] +[2023-02-26 12:14:09,839][10641] Saving new best policy, reward=21.821! +[2023-02-26 12:14:14,832][00595] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3842048. Throughput: 0: 880.6. Samples: 960288. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:14:14,837][00595] Avg episode reward: [(0, '21.413')] +[2023-02-26 12:14:16,628][10654] Updated weights for policy 0, policy_version 940 (0.0026) +[2023-02-26 12:14:19,832][00595] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 3858432. Throughput: 0: 871.8. Samples: 964330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-26 12:14:19,837][00595] Avg episode reward: [(0, '21.206')] +[2023-02-26 12:14:24,832][00595] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3721.2). Total num frames: 3878912. Throughput: 0: 905.4. Samples: 970930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:14:24,835][00595] Avg episode reward: [(0, '21.511')] +[2023-02-26 12:14:26,828][10654] Updated weights for policy 0, policy_version 950 (0.0025) +[2023-02-26 12:14:29,832][00595] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3748.9). Total num frames: 3903488. Throughput: 0: 906.8. Samples: 974246. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-26 12:14:29,841][00595] Avg episode reward: [(0, '20.575')] +[2023-02-26 12:14:34,833][00595] Fps is (10 sec: 3686.1, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3915776. Throughput: 0: 879.8. Samples: 979128. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:14:34,838][00595] Avg episode reward: [(0, '21.675')] +[2023-02-26 12:14:39,702][10654] Updated weights for policy 0, policy_version 960 (0.0019) +[2023-02-26 12:14:39,832][00595] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3932160. Throughput: 0: 878.9. Samples: 983390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:14:39,835][00595] Avg episode reward: [(0, '21.541')] +[2023-02-26 12:14:44,832][00595] Fps is (10 sec: 3686.7, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 3952640. Throughput: 0: 904.4. Samples: 986672. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-26 12:14:44,838][00595] Avg episode reward: [(0, '20.028')] +[2023-02-26 12:14:44,849][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000965_3952640.pth... +[2023-02-26 12:14:44,964][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000752_3080192.pth +[2023-02-26 12:14:48,758][10654] Updated weights for policy 0, policy_version 970 (0.0027) +[2023-02-26 12:14:49,835][00595] Fps is (10 sec: 4094.9, 60 sec: 3550.0, 300 sec: 3721.1). Total num frames: 3973120. Throughput: 0: 916.8. Samples: 993496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-26 12:14:49,839][00595] Avg episode reward: [(0, '19.995')] +[2023-02-26 12:14:54,834][00595] Fps is (10 sec: 3685.9, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3989504. Throughput: 0: 888.1. Samples: 998246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-26 12:14:54,838][00595] Avg episode reward: [(0, '19.304')] +[2023-02-26 12:14:59,646][10641] Stopping Batcher_0... +[2023-02-26 12:14:59,648][10641] Loop batcher_evt_loop terminating... +[2023-02-26 12:14:59,649][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-26 12:14:59,647][00595] Component Batcher_0 stopped! +[2023-02-26 12:14:59,700][10654] Weights refcount: 2 0 +[2023-02-26 12:14:59,703][00595] Component InferenceWorker_p0-w0 stopped! +[2023-02-26 12:14:59,706][10654] Stopping InferenceWorker_p0-w0... +[2023-02-26 12:14:59,708][10654] Loop inference_proc0-0_evt_loop terminating... +[2023-02-26 12:14:59,718][00595] Component RolloutWorker_w0 stopped! +[2023-02-26 12:14:59,718][10656] Stopping RolloutWorker_w0... +[2023-02-26 12:14:59,728][00595] Component RolloutWorker_w1 stopped! +[2023-02-26 12:14:59,730][10657] Stopping RolloutWorker_w1... +[2023-02-26 12:14:59,723][10656] Loop rollout_proc0_evt_loop terminating... +[2023-02-26 12:14:59,742][10657] Loop rollout_proc1_evt_loop terminating... +[2023-02-26 12:14:59,760][00595] Component RolloutWorker_w7 stopped! +[2023-02-26 12:14:59,770][10660] Stopping RolloutWorker_w4... +[2023-02-26 12:14:59,770][00595] Component RolloutWorker_w5 stopped! +[2023-02-26 12:14:59,779][10661] Stopping RolloutWorker_w5... +[2023-02-26 12:14:59,773][00595] Component RolloutWorker_w4 stopped! +[2023-02-26 12:14:59,780][10664] Stopping RolloutWorker_w6... +[2023-02-26 12:14:59,780][00595] Component RolloutWorker_w6 stopped! +[2023-02-26 12:14:59,773][10660] Loop rollout_proc4_evt_loop terminating... +[2023-02-26 12:14:59,786][10664] Loop rollout_proc6_evt_loop terminating... +[2023-02-26 12:14:59,791][10658] Stopping RolloutWorker_w2... +[2023-02-26 12:14:59,791][10658] Loop rollout_proc2_evt_loop terminating... +[2023-02-26 12:14:59,820][10641] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000859_3518464.pth +[2023-02-26 12:14:59,791][00595] Component RolloutWorker_w2 stopped! +[2023-02-26 12:14:59,762][10667] Stopping RolloutWorker_w7... +[2023-02-26 12:14:59,822][10667] Loop rollout_proc7_evt_loop terminating... +[2023-02-26 12:14:59,779][10661] Loop rollout_proc5_evt_loop terminating... +[2023-02-26 12:14:59,836][10659] Stopping RolloutWorker_w3... +[2023-02-26 12:14:59,838][10659] Loop rollout_proc3_evt_loop terminating... +[2023-02-26 12:14:59,837][00595] Component RolloutWorker_w3 stopped! +[2023-02-26 12:14:59,842][10641] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-26 12:15:00,023][00595] Component LearnerWorker_p0 stopped! +[2023-02-26 12:15:00,031][00595] Waiting for process learner_proc0 to stop... +[2023-02-26 12:15:00,037][10641] Stopping LearnerWorker_p0... +[2023-02-26 12:15:00,037][10641] Loop learner_proc0_evt_loop terminating... +[2023-02-26 12:15:02,009][00595] Waiting for process inference_proc0-0 to join... +[2023-02-26 12:15:02,419][00595] Waiting for process rollout_proc0 to join... +[2023-02-26 12:15:02,786][00595] Waiting for process rollout_proc1 to join... +[2023-02-26 12:15:02,787][00595] Waiting for process rollout_proc2 to join... +[2023-02-26 12:15:02,808][00595] Waiting for process rollout_proc3 to join... +[2023-02-26 12:15:02,810][00595] Waiting for process rollout_proc4 to join... +[2023-02-26 12:15:02,812][00595] Waiting for process rollout_proc5 to join... +[2023-02-26 12:15:02,817][00595] Waiting for process rollout_proc6 to join... +[2023-02-26 12:15:02,820][00595] Waiting for process rollout_proc7 to join... +[2023-02-26 12:15:02,821][00595] Batcher 0 profile tree view: +batching: 26.6436, releasing_batches: 0.0303 +[2023-02-26 12:15:02,823][00595] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0000 + wait_policy_total: 518.4513 +update_model: 7.4389 + weight_update: 0.0040 +one_step: 0.0023 + handle_policy_step: 497.7904 + deserialize: 14.6227, stack: 2.8471, obs_to_device_normalize: 111.5904, forward: 237.8848, send_messages: 25.4149 + prepare_outputs: 80.8594 + to_cpu: 50.8510 +[2023-02-26 12:15:02,831][00595] Learner 0 profile tree view: +misc: 0.0056, prepare_batch: 15.8218 +train: 75.5792 + epoch_init: 0.0216, minibatch_init: 0.0059, losses_postprocess: 0.5888, kl_divergence: 0.6031, after_optimizer: 33.1501 + calculate_losses: 26.7369 + losses_init: 0.0037, forward_head: 1.6081, bptt_initial: 17.8537, tail: 1.0629, advantages_returns: 0.3428, losses: 3.3359 + bptt: 2.2787 + bptt_forward_core: 2.2111 + update: 13.9088 + clip: 1.3861 +[2023-02-26 12:15:02,832][00595] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.2830, enqueue_policy_requests: 138.9609, env_step: 798.6116, overhead: 19.7832, complete_rollouts: 7.3900 +save_policy_outputs: 19.7255 + split_output_tensors: 9.4519 +[2023-02-26 12:15:02,834][00595] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3592, enqueue_policy_requests: 137.2622, env_step: 800.5373, overhead: 19.3391, complete_rollouts: 6.3508 +save_policy_outputs: 19.4753 + split_output_tensors: 9.3907 +[2023-02-26 12:15:02,836][00595] Loop Runner_EvtLoop terminating... +[2023-02-26 12:15:02,838][00595] Runner profile tree view: +main_loop: 1092.3718 +[2023-02-26 12:15:02,839][00595] Collected {0: 4005888}, FPS: 3667.1 +[2023-02-26 12:15:02,984][00595] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-26 12:15:02,987][00595] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-26 12:15:02,990][00595] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-26 12:15:02,992][00595] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-26 12:15:02,994][00595] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-26 12:15:02,996][00595] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-26 12:15:03,001][00595] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-02-26 12:15:03,004][00595] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-26 12:15:03,007][00595] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-02-26 12:15:03,008][00595] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-02-26 12:15:03,010][00595] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-26 12:15:03,012][00595] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-26 12:15:03,016][00595] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-26 12:15:03,018][00595] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-26 12:15:03,019][00595] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-26 12:15:03,043][00595] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-26 12:15:03,046][00595] RunningMeanStd input shape: (3, 72, 128) +[2023-02-26 12:15:03,048][00595] RunningMeanStd input shape: (1,) +[2023-02-26 12:15:03,065][00595] ConvEncoder: input_channels=3 +[2023-02-26 12:15:03,743][00595] Conv encoder output size: 512 +[2023-02-26 12:15:03,746][00595] Policy head output size: 512 +[2023-02-26 12:15:06,250][00595] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-26 12:15:07,567][00595] Num frames 100... +[2023-02-26 12:15:07,681][00595] Num frames 200... +[2023-02-26 12:15:07,797][00595] Num frames 300... +[2023-02-26 12:15:07,916][00595] Num frames 400... +[2023-02-26 12:15:08,037][00595] Num frames 500... +[2023-02-26 12:15:08,153][00595] Num frames 600... +[2023-02-26 12:15:08,271][00595] Num frames 700... +[2023-02-26 12:15:08,395][00595] Num frames 800... +[2023-02-26 12:15:08,513][00595] Num frames 900... +[2023-02-26 12:15:08,627][00595] Num frames 1000... +[2023-02-26 12:15:08,740][00595] Num frames 1100... +[2023-02-26 12:15:08,821][00595] Avg episode rewards: #0: 23.200, true rewards: #0: 11.200 +[2023-02-26 12:15:08,822][00595] Avg episode reward: 23.200, avg true_objective: 11.200 +[2023-02-26 12:15:08,917][00595] Num frames 1200... +[2023-02-26 12:15:09,036][00595] Num frames 1300... +[2023-02-26 12:15:09,146][00595] Num frames 1400... +[2023-02-26 12:15:09,267][00595] Num frames 1500... +[2023-02-26 12:15:09,380][00595] Num frames 1600... +[2023-02-26 12:15:09,496][00595] Num frames 1700... +[2023-02-26 12:15:09,629][00595] Num frames 1800... +[2023-02-26 12:15:09,788][00595] Num frames 1900... +[2023-02-26 12:15:09,950][00595] Num frames 2000... +[2023-02-26 12:15:10,119][00595] Num frames 2100... +[2023-02-26 12:15:10,294][00595] Num frames 2200... +[2023-02-26 12:15:10,475][00595] Num frames 2300... +[2023-02-26 12:15:10,639][00595] Num frames 2400... +[2023-02-26 12:15:10,806][00595] Num frames 2500... +[2023-02-26 12:15:10,973][00595] Num frames 2600... +[2023-02-26 12:15:11,072][00595] Avg episode rewards: #0: 29.620, true rewards: #0: 13.120 +[2023-02-26 12:15:11,075][00595] Avg episode reward: 29.620, avg true_objective: 13.120 +[2023-02-26 12:15:11,199][00595] Num frames 2700... +[2023-02-26 12:15:11,364][00595] Num frames 2800... +[2023-02-26 12:15:11,527][00595] Num frames 2900... +[2023-02-26 12:15:11,692][00595] Num frames 3000... +[2023-02-26 12:15:11,854][00595] Num frames 3100... +[2023-02-26 12:15:12,024][00595] Num frames 3200... +[2023-02-26 12:15:12,192][00595] Num frames 3300... +[2023-02-26 12:15:12,357][00595] Avg episode rewards: #0: 24.200, true rewards: #0: 11.200 +[2023-02-26 12:15:12,359][00595] Avg episode reward: 24.200, avg true_objective: 11.200 +[2023-02-26 12:15:12,426][00595] Num frames 3400... +[2023-02-26 12:15:12,588][00595] Num frames 3500... +[2023-02-26 12:15:12,746][00595] Num frames 3600... +[2023-02-26 12:15:12,831][00595] Avg episode rewards: #0: 18.790, true rewards: #0: 9.040 +[2023-02-26 12:15:12,833][00595] Avg episode reward: 18.790, avg true_objective: 9.040 +[2023-02-26 12:15:12,969][00595] Num frames 3700... +[2023-02-26 12:15:13,134][00595] Num frames 3800... +[2023-02-26 12:15:13,282][00595] Num frames 3900... +[2023-02-26 12:15:13,393][00595] Num frames 4000... +[2023-02-26 12:15:13,508][00595] Num frames 4100... +[2023-02-26 12:15:13,632][00595] Num frames 4200... +[2023-02-26 12:15:13,745][00595] Num frames 4300... +[2023-02-26 12:15:13,864][00595] Num frames 4400... +[2023-02-26 12:15:13,984][00595] Num frames 4500... +[2023-02-26 12:15:14,103][00595] Num frames 4600... +[2023-02-26 12:15:14,221][00595] Num frames 4700... +[2023-02-26 12:15:14,338][00595] Num frames 4800... +[2023-02-26 12:15:14,454][00595] Num frames 4900... +[2023-02-26 12:15:14,575][00595] Num frames 5000... +[2023-02-26 12:15:14,695][00595] Num frames 5100... +[2023-02-26 12:15:14,814][00595] Num frames 5200... +[2023-02-26 12:15:14,935][00595] Num frames 5300... +[2023-02-26 12:15:15,059][00595] Num frames 5400... +[2023-02-26 12:15:15,192][00595] Num frames 5500... +[2023-02-26 12:15:15,316][00595] Num frames 5600... +[2023-02-26 12:15:15,433][00595] Num frames 5700... +[2023-02-26 12:15:15,508][00595] Avg episode rewards: #0: 25.832, true rewards: #0: 11.432 +[2023-02-26 12:15:15,510][00595] Avg episode reward: 25.832, avg true_objective: 11.432 +[2023-02-26 12:15:15,607][00595] Num frames 5800... +[2023-02-26 12:15:15,730][00595] Num frames 5900... +[2023-02-26 12:15:15,848][00595] Num frames 6000... +[2023-02-26 12:15:15,972][00595] Num frames 6100... +[2023-02-26 12:15:16,091][00595] Num frames 6200... +[2023-02-26 12:15:16,204][00595] Num frames 6300... +[2023-02-26 12:15:16,327][00595] Num frames 6400... +[2023-02-26 12:15:16,443][00595] Num frames 6500... +[2023-02-26 12:15:16,561][00595] Num frames 6600... +[2023-02-26 12:15:16,691][00595] Num frames 6700... +[2023-02-26 12:15:16,815][00595] Num frames 6800... +[2023-02-26 12:15:16,945][00595] Num frames 6900... +[2023-02-26 12:15:17,065][00595] Num frames 7000... +[2023-02-26 12:15:17,185][00595] Num frames 7100... +[2023-02-26 12:15:17,318][00595] Num frames 7200... +[2023-02-26 12:15:17,437][00595] Num frames 7300... +[2023-02-26 12:15:17,568][00595] Num frames 7400... +[2023-02-26 12:15:17,700][00595] Num frames 7500... +[2023-02-26 12:15:17,822][00595] Num frames 7600... +[2023-02-26 12:15:17,906][00595] Avg episode rewards: #0: 29.200, true rewards: #0: 12.700 +[2023-02-26 12:15:17,908][00595] Avg episode reward: 29.200, avg true_objective: 12.700 +[2023-02-26 12:15:18,009][00595] Num frames 7700... +[2023-02-26 12:15:18,131][00595] Num frames 7800... +[2023-02-26 12:15:18,265][00595] Num frames 7900... +[2023-02-26 12:15:18,387][00595] Num frames 8000... +[2023-02-26 12:15:18,513][00595] Num frames 8100... +[2023-02-26 12:15:18,635][00595] Num frames 8200... +[2023-02-26 12:15:18,764][00595] Num frames 8300... +[2023-02-26 12:15:18,892][00595] Avg episode rewards: #0: 27.223, true rewards: #0: 11.937 +[2023-02-26 12:15:18,894][00595] Avg episode reward: 27.223, avg true_objective: 11.937 +[2023-02-26 12:15:18,953][00595] Num frames 8400... +[2023-02-26 12:15:19,078][00595] Num frames 8500... +[2023-02-26 12:15:19,200][00595] Num frames 8600... +[2023-02-26 12:15:19,329][00595] Num frames 8700... +[2023-02-26 12:15:19,450][00595] Num frames 8800... +[2023-02-26 12:15:19,573][00595] Num frames 8900... +[2023-02-26 12:15:19,669][00595] Avg episode rewards: #0: 25.040, true rewards: #0: 11.165 +[2023-02-26 12:15:19,673][00595] Avg episode reward: 25.040, avg true_objective: 11.165 +[2023-02-26 12:15:19,772][00595] Num frames 9000... +[2023-02-26 12:15:19,892][00595] Num frames 9100... +[2023-02-26 12:15:20,016][00595] Num frames 9200... +[2023-02-26 12:15:20,134][00595] Num frames 9300... +[2023-02-26 12:15:20,253][00595] Num frames 9400... +[2023-02-26 12:15:20,383][00595] Num frames 9500... +[2023-02-26 12:15:20,503][00595] Num frames 9600... +[2023-02-26 12:15:20,626][00595] Num frames 9700... +[2023-02-26 12:15:20,757][00595] Num frames 9800... +[2023-02-26 12:15:20,848][00595] Avg episode rewards: #0: 24.475, true rewards: #0: 10.920 +[2023-02-26 12:15:20,849][00595] Avg episode reward: 24.475, avg true_objective: 10.920 +[2023-02-26 12:15:20,942][00595] Num frames 9900... +[2023-02-26 12:15:21,070][00595] Num frames 10000... +[2023-02-26 12:15:21,187][00595] Num frames 10100... +[2023-02-26 12:15:21,316][00595] Num frames 10200... +[2023-02-26 12:15:21,432][00595] Num frames 10300... +[2023-02-26 12:15:21,550][00595] Num frames 10400... +[2023-02-26 12:15:21,690][00595] Avg episode rewards: #0: 23.268, true rewards: #0: 10.468 +[2023-02-26 12:15:21,693][00595] Avg episode reward: 23.268, avg true_objective: 10.468 +[2023-02-26 12:16:27,312][00595] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-02-26 12:20:20,559][00595] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-26 12:20:20,562][00595] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-26 12:20:20,564][00595] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-26 12:20:20,566][00595] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-26 12:20:20,567][00595] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-26 12:20:20,569][00595] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-26 12:20:20,572][00595] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-02-26 12:20:20,573][00595] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-26 12:20:20,574][00595] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-02-26 12:20:20,575][00595] Adding new argument 'hf_repository'='mikato/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-02-26 12:20:20,577][00595] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-26 12:20:20,579][00595] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-26 12:20:20,581][00595] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-26 12:20:20,582][00595] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-26 12:20:20,584][00595] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-26 12:20:20,612][00595] RunningMeanStd input shape: (3, 72, 128) +[2023-02-26 12:20:20,613][00595] RunningMeanStd input shape: (1,) +[2023-02-26 12:20:20,627][00595] ConvEncoder: input_channels=3 +[2023-02-26 12:20:20,664][00595] Conv encoder output size: 512 +[2023-02-26 12:20:20,665][00595] Policy head output size: 512 +[2023-02-26 12:20:20,684][00595] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-26 12:20:21,118][00595] Num frames 100... +[2023-02-26 12:20:21,236][00595] Num frames 200... +[2023-02-26 12:20:21,347][00595] Num frames 300... +[2023-02-26 12:20:21,464][00595] Num frames 400... +[2023-02-26 12:20:21,588][00595] Num frames 500... +[2023-02-26 12:20:21,698][00595] Num frames 600... +[2023-02-26 12:20:21,813][00595] Num frames 700... +[2023-02-26 12:20:21,925][00595] Num frames 800... +[2023-02-26 12:20:22,042][00595] Num frames 900... +[2023-02-26 12:20:22,164][00595] Num frames 1000... +[2023-02-26 12:20:22,283][00595] Num frames 1100... +[2023-02-26 12:20:22,396][00595] Num frames 1200... +[2023-02-26 12:20:22,512][00595] Num frames 1300... +[2023-02-26 12:20:22,632][00595] Num frames 1400... +[2023-02-26 12:20:22,770][00595] Avg episode rewards: #0: 35.720, true rewards: #0: 14.720 +[2023-02-26 12:20:22,772][00595] Avg episode reward: 35.720, avg true_objective: 14.720 +[2023-02-26 12:20:22,806][00595] Num frames 1500... +[2023-02-26 12:20:22,919][00595] Num frames 1600... +[2023-02-26 12:20:23,031][00595] Num frames 1700... +[2023-02-26 12:20:23,146][00595] Num frames 1800... +[2023-02-26 12:20:23,268][00595] Num frames 1900... +[2023-02-26 12:20:23,377][00595] Num frames 2000... +[2023-02-26 12:20:23,487][00595] Num frames 2100... +[2023-02-26 12:20:23,612][00595] Num frames 2200... +[2023-02-26 12:20:23,725][00595] Num frames 2300... +[2023-02-26 12:20:23,841][00595] Num frames 2400... +[2023-02-26 12:20:23,959][00595] Num frames 2500... +[2023-02-26 12:20:24,082][00595] Avg episode rewards: #0: 30.800, true rewards: #0: 12.800 +[2023-02-26 12:20:24,084][00595] Avg episode reward: 30.800, avg true_objective: 12.800 +[2023-02-26 12:20:24,131][00595] Num frames 2600... +[2023-02-26 12:20:24,247][00595] Num frames 2700... +[2023-02-26 12:20:24,358][00595] Num frames 2800... +[2023-02-26 12:20:24,471][00595] Num frames 2900... +[2023-02-26 12:20:24,587][00595] Num frames 3000... +[2023-02-26 12:20:24,706][00595] Num frames 3100... +[2023-02-26 12:20:24,817][00595] Num frames 3200... +[2023-02-26 12:20:24,931][00595] Num frames 3300... +[2023-02-26 12:20:25,050][00595] Num frames 3400... +[2023-02-26 12:20:25,161][00595] Num frames 3500... +[2023-02-26 12:20:25,284][00595] Num frames 3600... +[2023-02-26 12:20:25,427][00595] Avg episode rewards: #0: 29.600, true rewards: #0: 12.267 +[2023-02-26 12:20:25,429][00595] Avg episode reward: 29.600, avg true_objective: 12.267 +[2023-02-26 12:20:25,455][00595] Num frames 3700... +[2023-02-26 12:20:25,570][00595] Num frames 3800... +[2023-02-26 12:20:25,690][00595] Num frames 3900... +[2023-02-26 12:20:25,800][00595] Num frames 4000... +[2023-02-26 12:20:25,924][00595] Num frames 4100... +[2023-02-26 12:20:26,039][00595] Num frames 4200... +[2023-02-26 12:20:26,160][00595] Num frames 4300... +[2023-02-26 12:20:26,282][00595] Num frames 4400... +[2023-02-26 12:20:26,398][00595] Num frames 4500... +[2023-02-26 12:20:26,518][00595] Num frames 4600... +[2023-02-26 12:20:26,632][00595] Num frames 4700... +[2023-02-26 12:20:26,750][00595] Num frames 4800... +[2023-02-26 12:20:26,875][00595] Num frames 4900... +[2023-02-26 12:20:26,986][00595] Num frames 5000... +[2023-02-26 12:20:27,105][00595] Num frames 5100... +[2023-02-26 12:20:27,219][00595] Num frames 5200... +[2023-02-26 12:20:27,332][00595] Num frames 5300... +[2023-02-26 12:20:27,447][00595] Num frames 5400... +[2023-02-26 12:20:27,560][00595] Num frames 5500... +[2023-02-26 12:20:27,683][00595] Num frames 5600... +[2023-02-26 12:20:27,798][00595] Num frames 5700... +[2023-02-26 12:20:27,942][00595] Avg episode rewards: #0: 35.450, true rewards: #0: 14.450 +[2023-02-26 12:20:27,944][00595] Avg episode reward: 35.450, avg true_objective: 14.450 +[2023-02-26 12:20:27,973][00595] Num frames 5800... +[2023-02-26 12:20:28,100][00595] Num frames 5900... +[2023-02-26 12:20:28,215][00595] Num frames 6000... +[2023-02-26 12:20:28,330][00595] Num frames 6100... +[2023-02-26 12:20:28,443][00595] Num frames 6200... +[2023-02-26 12:20:28,612][00595] Num frames 6300... +[2023-02-26 12:20:28,776][00595] Num frames 6400... +[2023-02-26 12:20:28,945][00595] Num frames 6500... +[2023-02-26 12:20:29,106][00595] Num frames 6600... +[2023-02-26 12:20:29,273][00595] Num frames 6700... +[2023-02-26 12:20:29,427][00595] Num frames 6800... +[2023-02-26 12:20:29,592][00595] Num frames 6900... +[2023-02-26 12:20:29,797][00595] Avg episode rewards: #0: 33.974, true rewards: #0: 13.974 +[2023-02-26 12:20:29,800][00595] Avg episode reward: 33.974, avg true_objective: 13.974 +[2023-02-26 12:20:29,827][00595] Num frames 7000... +[2023-02-26 12:20:29,989][00595] Num frames 7100... +[2023-02-26 12:20:30,157][00595] Num frames 7200... +[2023-02-26 12:20:30,326][00595] Num frames 7300... +[2023-02-26 12:20:30,455][00595] Avg episode rewards: #0: 29.235, true rewards: #0: 12.235 +[2023-02-26 12:20:30,458][00595] Avg episode reward: 29.235, avg true_objective: 12.235 +[2023-02-26 12:20:30,557][00595] Num frames 7400... +[2023-02-26 12:20:30,722][00595] Num frames 7500... +[2023-02-26 12:20:30,896][00595] Num frames 7600... +[2023-02-26 12:20:31,063][00595] Num frames 7700... +[2023-02-26 12:20:31,226][00595] Num frames 7800... +[2023-02-26 12:20:31,391][00595] Num frames 7900... +[2023-02-26 12:20:31,475][00595] Avg episode rewards: #0: 26.453, true rewards: #0: 11.310 +[2023-02-26 12:20:31,478][00595] Avg episode reward: 26.453, avg true_objective: 11.310 +[2023-02-26 12:20:31,613][00595] Num frames 8000... +[2023-02-26 12:20:31,778][00595] Num frames 8100... +[2023-02-26 12:20:31,956][00595] Num frames 8200... +[2023-02-26 12:20:32,097][00595] Num frames 8300... +[2023-02-26 12:20:32,209][00595] Num frames 8400... +[2023-02-26 12:20:32,332][00595] Num frames 8500... +[2023-02-26 12:20:32,443][00595] Num frames 8600... +[2023-02-26 12:20:32,554][00595] Num frames 8700... +[2023-02-26 12:20:32,672][00595] Num frames 8800... +[2023-02-26 12:20:32,785][00595] Num frames 8900... +[2023-02-26 12:20:32,909][00595] Num frames 9000... +[2023-02-26 12:20:33,008][00595] Avg episode rewards: #0: 26.171, true rewards: #0: 11.296 +[2023-02-26 12:20:33,011][00595] Avg episode reward: 26.171, avg true_objective: 11.296 +[2023-02-26 12:20:33,082][00595] Num frames 9100... +[2023-02-26 12:20:33,196][00595] Num frames 9200... +[2023-02-26 12:20:33,319][00595] Num frames 9300... +[2023-02-26 12:20:33,433][00595] Num frames 9400... +[2023-02-26 12:20:33,543][00595] Num frames 9500... +[2023-02-26 12:20:33,652][00595] Num frames 9600... +[2023-02-26 12:20:33,771][00595] Num frames 9700... +[2023-02-26 12:20:33,889][00595] Num frames 9800... +[2023-02-26 12:20:34,011][00595] Num frames 9900... +[2023-02-26 12:20:34,126][00595] Num frames 10000... +[2023-02-26 12:20:34,240][00595] Num frames 10100... +[2023-02-26 12:20:34,360][00595] Num frames 10200... +[2023-02-26 12:20:34,464][00595] Avg episode rewards: #0: 26.046, true rewards: #0: 11.379 +[2023-02-26 12:20:34,465][00595] Avg episode reward: 26.046, avg true_objective: 11.379 +[2023-02-26 12:20:34,533][00595] Num frames 10300... +[2023-02-26 12:20:34,644][00595] Num frames 10400... +[2023-02-26 12:20:34,767][00595] Num frames 10500... +[2023-02-26 12:20:34,889][00595] Num frames 10600... +[2023-02-26 12:20:35,012][00595] Num frames 10700... +[2023-02-26 12:20:35,125][00595] Num frames 10800... +[2023-02-26 12:20:35,238][00595] Num frames 10900... +[2023-02-26 12:20:35,313][00595] Avg episode rewards: #0: 24.816, true rewards: #0: 10.916 +[2023-02-26 12:20:35,315][00595] Avg episode reward: 24.816, avg true_objective: 10.916 +[2023-02-26 12:21:40,672][00595] Replay video saved to /content/train_dir/default_experiment/replay.mp4!