diff --git "a/sf_log.txt" "b/sf_log.txt"
new file mode 100644--- /dev/null
+++ "b/sf_log.txt"
@@ -0,0 +1,1229 @@
+[2023-02-25 18:43:57,962][00219] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-02-25 18:43:57,966][00219] Rollout worker 0 uses device cpu
+[2023-02-25 18:43:57,969][00219] Rollout worker 1 uses device cpu
+[2023-02-25 18:43:57,971][00219] Rollout worker 2 uses device cpu
+[2023-02-25 18:43:57,972][00219] Rollout worker 3 uses device cpu
+[2023-02-25 18:43:57,973][00219] Rollout worker 4 uses device cpu
+[2023-02-25 18:43:57,975][00219] Rollout worker 5 uses device cpu
+[2023-02-25 18:43:57,976][00219] Rollout worker 6 uses device cpu
+[2023-02-25 18:43:57,977][00219] Rollout worker 7 uses device cpu
+[2023-02-25 18:43:58,173][00219] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 18:43:58,177][00219] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-25 18:43:58,212][00219] Starting all processes...
+[2023-02-25 18:43:58,214][00219] Starting process learner_proc0
+[2023-02-25 18:43:58,264][00219] Starting all processes...
+[2023-02-25 18:43:58,272][00219] Starting process inference_proc0-0
+[2023-02-25 18:43:58,273][00219] Starting process rollout_proc0
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc1
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc2
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc3
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc4
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc5
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc6
+[2023-02-25 18:43:58,275][00219] Starting process rollout_proc7
+[2023-02-25 18:44:09,268][12589] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 18:44:09,270][12589] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-02-25 18:44:09,401][12607] Worker 4 uses CPU cores [0]
+[2023-02-25 18:44:09,457][12610] Worker 6 uses CPU cores [0]
+[2023-02-25 18:44:09,597][12605] Worker 1 uses CPU cores [1]
+[2023-02-25 18:44:09,605][12608] Worker 3 uses CPU cores [1]
+[2023-02-25 18:44:09,668][12603] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 18:44:09,672][12603] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-02-25 18:44:09,694][12609] Worker 5 uses CPU cores [1]
+[2023-02-25 18:44:09,733][12604] Worker 0 uses CPU cores [0]
+[2023-02-25 18:44:09,764][12606] Worker 2 uses CPU cores [0]
+[2023-02-25 18:44:09,825][12611] Worker 7 uses CPU cores [1]
+[2023-02-25 18:44:10,218][12589] Num visible devices: 1
+[2023-02-25 18:44:10,219][12603] Num visible devices: 1
+[2023-02-25 18:44:10,232][12589] Starting seed is not provided
+[2023-02-25 18:44:10,232][12589] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 18:44:10,232][12589] Initializing actor-critic model on device cuda:0
+[2023-02-25 18:44:10,233][12589] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 18:44:10,235][12589] RunningMeanStd input shape: (1,)
+[2023-02-25 18:44:10,247][12589] ConvEncoder: input_channels=3
+[2023-02-25 18:44:10,525][12589] Conv encoder output size: 512
+[2023-02-25 18:44:10,526][12589] Policy head output size: 512
+[2023-02-25 18:44:10,588][12589] Created Actor Critic model with architecture:
+[2023-02-25 18:44:10,588][12589] 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)
+  )
+)
+[2023-02-25 18:44:18,166][00219] Heartbeat connected on Batcher_0
+[2023-02-25 18:44:18,173][00219] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-25 18:44:18,185][00219] Heartbeat connected on RolloutWorker_w0
+[2023-02-25 18:44:18,188][00219] Heartbeat connected on RolloutWorker_w1
+[2023-02-25 18:44:18,192][00219] Heartbeat connected on RolloutWorker_w2
+[2023-02-25 18:44:18,196][00219] Heartbeat connected on RolloutWorker_w3
+[2023-02-25 18:44:18,201][00219] Heartbeat connected on RolloutWorker_w4
+[2023-02-25 18:44:18,204][00219] Heartbeat connected on RolloutWorker_w5
+[2023-02-25 18:44:18,207][00219] Heartbeat connected on RolloutWorker_w6
+[2023-02-25 18:44:18,210][00219] Heartbeat connected on RolloutWorker_w7
+[2023-02-25 18:44:18,380][12589] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-25 18:44:18,382][12589] No checkpoints found
+[2023-02-25 18:44:18,382][12589] Did not load from checkpoint, starting from scratch!
+[2023-02-25 18:44:18,383][12589] Initialized policy 0 weights for model version 0
+[2023-02-25 18:44:18,386][12589] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-25 18:44:18,393][12589] LearnerWorker_p0 finished initialization!
+[2023-02-25 18:44:18,394][00219] Heartbeat connected on LearnerWorker_p0
+[2023-02-25 18:44:18,475][00219] 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)
+[2023-02-25 18:44:18,592][12603] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 18:44:18,593][12603] RunningMeanStd input shape: (1,)
+[2023-02-25 18:44:18,605][12603] ConvEncoder: input_channels=3
+[2023-02-25 18:44:18,704][12603] Conv encoder output size: 512
+[2023-02-25 18:44:18,705][12603] Policy head output size: 512
+[2023-02-25 18:44:21,257][00219] Inference worker 0-0 is ready!
+[2023-02-25 18:44:21,260][00219] All inference workers are ready! Signal rollout workers to start!
+[2023-02-25 18:44:21,391][12609] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,402][12611] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,420][12608] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,422][12605] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,488][12604] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,518][12607] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,523][12610] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:21,534][12606] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 18:44:23,005][12611] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:23,006][12608] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:23,006][12606] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:23,016][12605] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:23,017][12609] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:23,474][00219] 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)
+[2023-02-25 18:44:23,931][12605] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:23,940][12608] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:24,449][12604] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:24,451][12607] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:24,485][12606] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:25,260][12611] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:25,506][12608] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:25,808][12604] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:25,888][12607] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:26,007][12605] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:26,115][12606] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:26,620][12610] Decorrelating experience for 0 frames...
+[2023-02-25 18:44:27,129][12611] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:27,243][12608] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:27,357][12604] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:27,364][12610] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:27,399][12609] Decorrelating experience for 32 frames...
+[2023-02-25 18:44:27,594][12605] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:28,300][12611] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:28,396][12607] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:28,459][12609] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:28,477][00219] 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)
+[2023-02-25 18:44:28,629][12604] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:28,865][12609] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:29,335][12606] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:29,434][12610] Decorrelating experience for 64 frames...
+[2023-02-25 18:44:29,741][12607] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:30,071][12610] Decorrelating experience for 96 frames...
+[2023-02-25 18:44:33,474][00219] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 125.9. Samples: 1888. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-25 18:44:33,481][00219] Avg episode reward: [(0, '1.546')]
+[2023-02-25 18:44:33,723][12589] Signal inference workers to stop experience collection...
+[2023-02-25 18:44:33,755][12603] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-25 18:44:36,237][12589] Signal inference workers to resume experience collection...
+[2023-02-25 18:44:36,238][12603] InferenceWorker_p0-w0: resuming experience collection
+[2023-02-25 18:44:38,475][00219] Fps is (10 sec: 409.7, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 112.2. Samples: 2244. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2023-02-25 18:44:38,481][00219] Avg episode reward: [(0, '2.260')]
+[2023-02-25 18:44:43,474][00219] Fps is (10 sec: 2048.0, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 20480. Throughput: 0: 229.9. Samples: 5748. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:44:43,476][00219] Avg episode reward: [(0, '3.448')]
+[2023-02-25 18:44:47,940][12603] Updated weights for policy 0, policy_version 10 (0.0030)
+[2023-02-25 18:44:48,474][00219] Fps is (10 sec: 3686.7, 60 sec: 1365.4, 300 sec: 1365.4). Total num frames: 40960. Throughput: 0: 371.2. Samples: 11136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:44:48,482][00219] Avg episode reward: [(0, '4.223')]
+[2023-02-25 18:44:53,474][00219] Fps is (10 sec: 4505.6, 60 sec: 1872.5, 300 sec: 1872.5). Total num frames: 65536. Throughput: 0: 416.5. Samples: 14578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:44:53,476][00219] Avg episode reward: [(0, '4.598')]
+[2023-02-25 18:44:57,383][12603] Updated weights for policy 0, policy_version 20 (0.0022)
+[2023-02-25 18:44:58,474][00219] Fps is (10 sec: 4096.0, 60 sec: 2048.1, 300 sec: 2048.1). Total num frames: 81920. Throughput: 0: 525.1. Samples: 21002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:44:58,476][00219] Avg episode reward: [(0, '4.443')]
+[2023-02-25 18:45:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 2184.6, 300 sec: 2184.6). Total num frames: 98304. Throughput: 0: 566.5. Samples: 25494. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:45:03,481][00219] Avg episode reward: [(0, '4.268')]
+[2023-02-25 18:45:08,474][00219] Fps is (10 sec: 3686.3, 60 sec: 2375.7, 300 sec: 2375.7). Total num frames: 118784. Throughput: 0: 622.3. Samples: 28002. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2023-02-25 18:45:08,476][00219] Avg episode reward: [(0, '4.393')]
+[2023-02-25 18:45:08,492][12589] Saving new best policy, reward=4.393!
+[2023-02-25 18:45:09,211][12603] Updated weights for policy 0, policy_version 30 (0.0021)
+[2023-02-25 18:45:13,474][00219] Fps is (10 sec: 4096.0, 60 sec: 2532.1, 300 sec: 2532.1). Total num frames: 139264. Throughput: 0: 774.4. Samples: 34846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:13,479][00219] Avg episode reward: [(0, '4.496')]
+[2023-02-25 18:45:13,487][12589] Saving new best policy, reward=4.496!
+[2023-02-25 18:45:18,482][00219] Fps is (10 sec: 4092.8, 60 sec: 2662.1, 300 sec: 2662.1). Total num frames: 159744. Throughput: 0: 863.9. Samples: 40772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:18,486][00219] Avg episode reward: [(0, '4.528')]
+[2023-02-25 18:45:18,491][12589] Saving new best policy, reward=4.528!
+[2023-02-25 18:45:19,448][12603] Updated weights for policy 0, policy_version 40 (0.0023)
+[2023-02-25 18:45:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2646.7). Total num frames: 172032. Throughput: 0: 903.6. Samples: 42904. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:45:23,481][00219] Avg episode reward: [(0, '4.374')]
+[2023-02-25 18:45:28,474][00219] Fps is (10 sec: 3279.4, 60 sec: 3208.7, 300 sec: 2750.2). Total num frames: 192512. Throughput: 0: 940.2. Samples: 48058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:28,477][00219] Avg episode reward: [(0, '4.430')]
+[2023-02-25 18:45:30,539][12603] Updated weights for policy 0, policy_version 50 (0.0021)
+[2023-02-25 18:45:33,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 2894.5). Total num frames: 217088. Throughput: 0: 974.6. Samples: 54994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:45:33,480][00219] Avg episode reward: [(0, '4.384')]
+[2023-02-25 18:45:38,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 2918.4). Total num frames: 233472. Throughput: 0: 970.2. Samples: 58238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:38,476][00219] Avg episode reward: [(0, '4.359')]
+[2023-02-25 18:45:41,434][12603] Updated weights for policy 0, policy_version 60 (0.0035)
+[2023-02-25 18:45:43,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 2939.5). Total num frames: 249856. Throughput: 0: 924.9. Samples: 62622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:45:43,479][00219] Avg episode reward: [(0, '4.487')]
+[2023-02-25 18:45:48,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3003.8). Total num frames: 270336. Throughput: 0: 952.5. Samples: 68358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:48,478][00219] Avg episode reward: [(0, '4.503')]
+[2023-02-25 18:45:51,650][12603] Updated weights for policy 0, policy_version 70 (0.0027)
+[2023-02-25 18:45:53,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3061.3). Total num frames: 290816. Throughput: 0: 974.4. Samples: 71850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:45:53,476][00219] Avg episode reward: [(0, '4.496')]
+[2023-02-25 18:45:53,494][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth...
+[2023-02-25 18:45:58,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3113.0). Total num frames: 311296. Throughput: 0: 955.6. Samples: 77846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:45:58,476][00219] Avg episode reward: [(0, '4.388')]
+[2023-02-25 18:46:03,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3081.8). Total num frames: 323584. Throughput: 0: 923.0. Samples: 82302. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:46:03,480][00219] Avg episode reward: [(0, '4.505')]
+[2023-02-25 18:46:03,593][12603] Updated weights for policy 0, policy_version 80 (0.0018)
+[2023-02-25 18:46:08,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3127.9). Total num frames: 344064. Throughput: 0: 937.4. Samples: 85088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:46:08,479][00219] Avg episode reward: [(0, '4.456')]
+[2023-02-25 18:46:12,984][12603] Updated weights for policy 0, policy_version 90 (0.0018)
+[2023-02-25 18:46:13,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3205.6). Total num frames: 368640. Throughput: 0: 976.4. Samples: 91998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:46:13,479][00219] Avg episode reward: [(0, '4.437')]
+[2023-02-25 18:46:18,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3755.2, 300 sec: 3208.6). Total num frames: 385024. Throughput: 0: 944.4. Samples: 97490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:46:18,481][00219] Avg episode reward: [(0, '4.592')]
+[2023-02-25 18:46:18,484][12589] Saving new best policy, reward=4.592!
+[2023-02-25 18:46:23,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3178.5). Total num frames: 397312. Throughput: 0: 907.9. Samples: 99092. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:46:23,476][00219] Avg episode reward: [(0, '4.712')]
+[2023-02-25 18:46:23,490][12589] Saving new best policy, reward=4.712!
+[2023-02-25 18:46:28,054][12603] Updated weights for policy 0, policy_version 100 (0.0017)
+[2023-02-25 18:46:28,474][00219] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3150.8). Total num frames: 409600. Throughput: 0: 884.6. Samples: 102430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:46:28,477][00219] Avg episode reward: [(0, '4.731')]
+[2023-02-25 18:46:28,480][12589] Saving new best policy, reward=4.731!
+[2023-02-25 18:46:33,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3155.5). Total num frames: 425984. Throughput: 0: 875.6. Samples: 107760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:46:33,476][00219] Avg episode reward: [(0, '4.621')]
+[2023-02-25 18:46:38,120][12603] Updated weights for policy 0, policy_version 110 (0.0020)
+[2023-02-25 18:46:38,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3218.3). Total num frames: 450560. Throughput: 0: 876.0. Samples: 111272. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:46:38,478][00219] Avg episode reward: [(0, '4.587')]
+[2023-02-25 18:46:43,474][00219] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3192.1). Total num frames: 462848. Throughput: 0: 852.7. Samples: 116218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:46:43,476][00219] Avg episode reward: [(0, '4.599')]
+[2023-02-25 18:46:48,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3194.9). Total num frames: 479232. Throughput: 0: 862.5. Samples: 121116. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:46:48,476][00219] Avg episode reward: [(0, '4.579')]
+[2023-02-25 18:46:50,248][12603] Updated weights for policy 0, policy_version 120 (0.0017)
+[2023-02-25 18:46:53,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3250.4). Total num frames: 503808. Throughput: 0: 877.8. Samples: 124590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:46:53,476][00219] Avg episode reward: [(0, '4.656')]
+[2023-02-25 18:46:58,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 524288. Throughput: 0: 879.1. Samples: 131558. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:46:58,483][00219] Avg episode reward: [(0, '4.637')]
+[2023-02-25 18:47:00,203][12603] Updated weights for policy 0, policy_version 130 (0.0031)
+[2023-02-25 18:47:03,474][00219] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 540672. Throughput: 0: 856.1. Samples: 136014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:47:03,481][00219] Avg episode reward: [(0, '4.814')]
+[2023-02-25 18:47:03,496][12589] Saving new best policy, reward=4.814!
+[2023-02-25 18:47:08,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 557056. Throughput: 0: 869.7. Samples: 138228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:47:08,476][00219] Avg episode reward: [(0, '4.832')]
+[2023-02-25 18:47:08,487][12589] Saving new best policy, reward=4.832!
+[2023-02-25 18:47:11,638][12603] Updated weights for policy 0, policy_version 140 (0.0015)
+[2023-02-25 18:47:13,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 938.0. Samples: 144642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:47:13,476][00219] Avg episode reward: [(0, '4.985')]
+[2023-02-25 18:47:13,487][12589] Saving new best policy, reward=4.985!
+[2023-02-25 18:47:18,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 964.9. Samples: 151180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:47:18,477][00219] Avg episode reward: [(0, '4.926')]
+[2023-02-25 18:47:22,365][12603] Updated weights for policy 0, policy_version 150 (0.0011)
+[2023-02-25 18:47:23,478][00219] Fps is (10 sec: 3275.5, 60 sec: 3617.9, 300 sec: 3321.0). Total num frames: 614400. Throughput: 0: 936.3. Samples: 153410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:47:23,481][00219] Avg episode reward: [(0, '4.939')]
+[2023-02-25 18:47:28,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3319.9). Total num frames: 630784. Throughput: 0: 925.0. Samples: 157842. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:47:28,477][00219] Avg episode reward: [(0, '4.984')]
+[2023-02-25 18:47:32,986][12603] Updated weights for policy 0, policy_version 160 (0.0015)
+[2023-02-25 18:47:33,474][00219] Fps is (10 sec: 4097.6, 60 sec: 3822.9, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 967.8. Samples: 164668. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:47:33,476][00219] Avg episode reward: [(0, '4.968')]
+[2023-02-25 18:47:38,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3379.2). Total num frames: 675840. Throughput: 0: 968.3. Samples: 168164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:47:38,482][00219] Avg episode reward: [(0, '4.849')]
+[2023-02-25 18:47:43,476][00219] Fps is (10 sec: 3685.5, 60 sec: 3822.8, 300 sec: 3376.7). Total num frames: 692224. Throughput: 0: 917.2. Samples: 172832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:47:43,481][00219] Avg episode reward: [(0, '4.887')]
+[2023-02-25 18:47:44,900][12603] Updated weights for policy 0, policy_version 170 (0.0017)
+[2023-02-25 18:47:48,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3374.3). Total num frames: 708608. Throughput: 0: 930.9. Samples: 177904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:47:48,482][00219] Avg episode reward: [(0, '4.971')]
+[2023-02-25 18:47:53,474][00219] Fps is (10 sec: 4096.9, 60 sec: 3822.9, 300 sec: 3410.2). Total num frames: 733184. Throughput: 0: 958.6. Samples: 181366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:47:53,481][00219] Avg episode reward: [(0, '4.837')]
+[2023-02-25 18:47:53,494][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000179_733184.pth...
+[2023-02-25 18:47:54,224][12603] Updated weights for policy 0, policy_version 180 (0.0020)
+[2023-02-25 18:47:58,474][00219] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3425.8). Total num frames: 753664. Throughput: 0: 970.9. Samples: 188332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:47:58,480][00219] Avg episode reward: [(0, '5.002')]
+[2023-02-25 18:47:58,483][12589] Saving new best policy, reward=5.002!
+[2023-02-25 18:48:03,477][00219] Fps is (10 sec: 3275.8, 60 sec: 3754.5, 300 sec: 3404.2). Total num frames: 765952. Throughput: 0: 923.8. Samples: 192752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:48:03,482][00219] Avg episode reward: [(0, '5.009')]
+[2023-02-25 18:48:03,499][12589] Saving new best policy, reward=5.009!
+[2023-02-25 18:48:06,428][12603] Updated weights for policy 0, policy_version 190 (0.0020)
+[2023-02-25 18:48:08,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3419.3). Total num frames: 786432. Throughput: 0: 923.9. Samples: 194984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:48:08,481][00219] Avg episode reward: [(0, '5.056')]
+[2023-02-25 18:48:08,485][12589] Saving new best policy, reward=5.056!
+[2023-02-25 18:48:13,474][00219] Fps is (10 sec: 4506.9, 60 sec: 3822.9, 300 sec: 3451.1). Total num frames: 811008. Throughput: 0: 983.1. Samples: 202082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:48:13,476][00219] Avg episode reward: [(0, '5.241')]
+[2023-02-25 18:48:13,489][12589] Saving new best policy, reward=5.241!
+[2023-02-25 18:48:15,030][12603] Updated weights for policy 0, policy_version 200 (0.0011)
+[2023-02-25 18:48:18,480][00219] Fps is (10 sec: 4502.9, 60 sec: 3822.6, 300 sec: 3464.5). Total num frames: 831488. Throughput: 0: 970.8. Samples: 208358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:48:18,482][00219] Avg episode reward: [(0, '5.708')]
+[2023-02-25 18:48:18,490][12589] Saving new best policy, reward=5.708!
+[2023-02-25 18:48:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3823.2, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 941.9. Samples: 210548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:48:23,476][00219] Avg episode reward: [(0, '5.742')]
+[2023-02-25 18:48:23,498][12589] Saving new best policy, reward=5.742!
+[2023-02-25 18:48:27,641][12603] Updated weights for policy 0, policy_version 210 (0.0015)
+[2023-02-25 18:48:28,474][00219] Fps is (10 sec: 2868.9, 60 sec: 3822.9, 300 sec: 3440.7). Total num frames: 860160. Throughput: 0: 944.1. Samples: 215314. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:48:28,480][00219] Avg episode reward: [(0, '5.680')]
+[2023-02-25 18:48:33,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3469.6). Total num frames: 884736. Throughput: 0: 987.7. Samples: 222350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:48:33,476][00219] Avg episode reward: [(0, '5.768')]
+[2023-02-25 18:48:33,497][12589] Saving new best policy, reward=5.768!
+[2023-02-25 18:48:36,461][12603] Updated weights for policy 0, policy_version 220 (0.0018)
+[2023-02-25 18:48:38,475][00219] Fps is (10 sec: 4504.8, 60 sec: 3822.8, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 984.6. Samples: 225674. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:48:38,478][00219] Avg episode reward: [(0, '6.026')]
+[2023-02-25 18:48:38,485][12589] Saving new best policy, reward=6.026!
+[2023-02-25 18:48:43,474][00219] Fps is (10 sec: 3276.6, 60 sec: 3754.8, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 923.6. Samples: 229894. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:48:43,477][00219] Avg episode reward: [(0, '6.105')]
+[2023-02-25 18:48:43,490][12589] Saving new best policy, reward=6.105!
+[2023-02-25 18:48:48,474][00219] Fps is (10 sec: 3277.4, 60 sec: 3823.0, 300 sec: 3474.0). Total num frames: 937984. Throughput: 0: 950.3. Samples: 235512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:48:48,476][00219] Avg episode reward: [(0, '5.425')]
+[2023-02-25 18:48:48,701][12603] Updated weights for policy 0, policy_version 230 (0.0019)
+[2023-02-25 18:48:53,474][00219] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3485.3). Total num frames: 958464. Throughput: 0: 963.9. Samples: 238360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:48:53,476][00219] Avg episode reward: [(0, '5.559')]
+[2023-02-25 18:48:58,477][00219] Fps is (10 sec: 4094.8, 60 sec: 3754.5, 300 sec: 3496.2). Total num frames: 978944. Throughput: 0: 944.2. Samples: 244574. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:48:58,480][00219] Avg episode reward: [(0, '6.195')]
+[2023-02-25 18:48:58,486][12589] Saving new best policy, reward=6.195!
+[2023-02-25 18:48:59,687][12603] Updated weights for policy 0, policy_version 240 (0.0013)
+[2023-02-25 18:49:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3478.0). Total num frames: 991232. Throughput: 0: 901.4. Samples: 248914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:49:03,482][00219] Avg episode reward: [(0, '5.986')]
+[2023-02-25 18:49:08,474][00219] Fps is (10 sec: 3277.8, 60 sec: 3754.7, 300 sec: 3488.7). Total num frames: 1011712. Throughput: 0: 914.1. Samples: 251684. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:49:08,483][00219] Avg episode reward: [(0, '6.334')]
+[2023-02-25 18:49:08,486][12589] Saving new best policy, reward=6.334!
+[2023-02-25 18:49:10,430][12603] Updated weights for policy 0, policy_version 250 (0.0011)
+[2023-02-25 18:49:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3512.9). Total num frames: 1036288. Throughput: 0: 964.3. Samples: 258706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:49:13,478][00219] Avg episode reward: [(0, '6.680')]
+[2023-02-25 18:49:13,492][12589] Saving new best policy, reward=6.680!
+[2023-02-25 18:49:18,475][00219] Fps is (10 sec: 4095.6, 60 sec: 3686.7, 300 sec: 3568.4). Total num frames: 1052672. Throughput: 0: 933.2. Samples: 264344. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:49:18,479][00219] Avg episode reward: [(0, '6.622')]
+[2023-02-25 18:49:21,615][12603] Updated weights for policy 0, policy_version 260 (0.0019)
+[2023-02-25 18:49:23,476][00219] Fps is (10 sec: 3276.2, 60 sec: 3754.5, 300 sec: 3623.9). Total num frames: 1069056. Throughput: 0: 910.7. Samples: 266656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:49:23,483][00219] Avg episode reward: [(0, '6.558')]
+[2023-02-25 18:49:28,474][00219] Fps is (10 sec: 3686.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1089536. Throughput: 0: 942.0. Samples: 272286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:49:28,480][00219] Avg episode reward: [(0, '6.452')]
+[2023-02-25 18:49:31,377][12603] Updated weights for policy 0, policy_version 270 (0.0011)
+[2023-02-25 18:49:33,474][00219] Fps is (10 sec: 4506.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1114112. Throughput: 0: 973.7. Samples: 279328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:49:33,476][00219] Avg episode reward: [(0, '6.595')]
+[2023-02-25 18:49:38,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3754.8, 300 sec: 3762.8). Total num frames: 1130496. Throughput: 0: 976.1. Samples: 282284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:49:38,479][00219] Avg episode reward: [(0, '6.517')]
+[2023-02-25 18:49:42,951][12603] Updated weights for policy 0, policy_version 280 (0.0014)
+[2023-02-25 18:49:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 1146880. Throughput: 0: 940.1. Samples: 286874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:49:43,484][00219] Avg episode reward: [(0, '7.447')]
+[2023-02-25 18:49:43,502][12589] Saving new best policy, reward=7.447!
+[2023-02-25 18:49:48,474][00219] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1167360. Throughput: 0: 978.9. Samples: 292964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:49:48,476][00219] Avg episode reward: [(0, '7.907')]
+[2023-02-25 18:49:48,479][12589] Saving new best policy, reward=7.907!
+[2023-02-25 18:49:52,337][12603] Updated weights for policy 0, policy_version 290 (0.0020)
+[2023-02-25 18:49:53,474][00219] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1191936. Throughput: 0: 993.3. Samples: 296382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:49:53,481][00219] Avg episode reward: [(0, '7.722')]
+[2023-02-25 18:49:53,493][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000291_1191936.pth...
+[2023-02-25 18:49:53,600][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth
+[2023-02-25 18:49:58,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3823.1, 300 sec: 3762.8). Total num frames: 1208320. Throughput: 0: 969.3. Samples: 302324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:49:58,481][00219] Avg episode reward: [(0, '7.716')]
+[2023-02-25 18:50:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1224704. Throughput: 0: 941.1. Samples: 306692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:50:03,479][00219] Avg episode reward: [(0, '7.865')]
+[2023-02-25 18:50:04,793][12603] Updated weights for policy 0, policy_version 300 (0.0017)
+[2023-02-25 18:50:08,474][00219] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 1245184. Throughput: 0: 955.0. Samples: 309628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:50:08,481][00219] Avg episode reward: [(0, '7.428')]
+[2023-02-25 18:50:13,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3749.0). Total num frames: 1265664. Throughput: 0: 982.8. Samples: 316514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:50:13,476][00219] Avg episode reward: [(0, '7.632')]
+[2023-02-25 18:50:13,646][12603] Updated weights for policy 0, policy_version 310 (0.0011)
+[2023-02-25 18:50:18,474][00219] Fps is (10 sec: 3686.5, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 1282048. Throughput: 0: 940.9. Samples: 321670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:50:18,483][00219] Avg episode reward: [(0, '8.313')]
+[2023-02-25 18:50:18,486][12589] Saving new best policy, reward=8.313!
+[2023-02-25 18:50:23,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 1298432. Throughput: 0: 922.3. Samples: 323786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:50:23,479][00219] Avg episode reward: [(0, '8.524')]
+[2023-02-25 18:50:23,490][12589] Saving new best policy, reward=8.524!
+[2023-02-25 18:50:26,223][12603] Updated weights for policy 0, policy_version 320 (0.0011)
+[2023-02-25 18:50:28,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 1318912. Throughput: 0: 946.1. Samples: 329450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:50:28,481][00219] Avg episode reward: [(0, '8.948')]
+[2023-02-25 18:50:28,484][12589] Saving new best policy, reward=8.948!
+[2023-02-25 18:50:33,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1343488. Throughput: 0: 964.9. Samples: 336384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:50:33,476][00219] Avg episode reward: [(0, '9.104')]
+[2023-02-25 18:50:33,484][12589] Saving new best policy, reward=9.104!
+[2023-02-25 18:50:35,843][12603] Updated weights for policy 0, policy_version 330 (0.0013)
+[2023-02-25 18:50:38,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1355776. Throughput: 0: 941.3. Samples: 338742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:50:38,480][00219] Avg episode reward: [(0, '9.298')]
+[2023-02-25 18:50:38,551][12589] Saving new best policy, reward=9.298!
+[2023-02-25 18:50:43,474][00219] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1372160. Throughput: 0: 907.6. Samples: 343164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:50:43,482][00219] Avg episode reward: [(0, '10.035')]
+[2023-02-25 18:50:43,493][12589] Saving new best policy, reward=10.035!
+[2023-02-25 18:50:47,461][12603] Updated weights for policy 0, policy_version 340 (0.0015)
+[2023-02-25 18:50:48,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1396736. Throughput: 0: 954.1. Samples: 349628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:50:48,476][00219] Avg episode reward: [(0, '11.035')]
+[2023-02-25 18:50:48,481][12589] Saving new best policy, reward=11.035!
+[2023-02-25 18:50:53,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1417216. Throughput: 0: 965.3. Samples: 353068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:50:53,476][00219] Avg episode reward: [(0, '11.494')]
+[2023-02-25 18:50:53,562][12589] Saving new best policy, reward=11.494!
+[2023-02-25 18:50:57,756][12603] Updated weights for policy 0, policy_version 350 (0.0019)
+[2023-02-25 18:50:58,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1433600. Throughput: 0: 936.0. Samples: 358634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:50:58,478][00219] Avg episode reward: [(0, '11.011')]
+[2023-02-25 18:51:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1449984. Throughput: 0: 922.8. Samples: 363194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:51:03,476][00219] Avg episode reward: [(0, '10.271')]
+[2023-02-25 18:51:08,312][12603] Updated weights for policy 0, policy_version 360 (0.0019)
+[2023-02-25 18:51:08,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 1474560. Throughput: 0: 953.1. Samples: 366676. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:51:08,476][00219] Avg episode reward: [(0, '9.879')]
+[2023-02-25 18:51:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1495040. Throughput: 0: 987.5. Samples: 373886. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:51:13,478][00219] Avg episode reward: [(0, '9.359')]
+[2023-02-25 18:51:18,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 1511424. Throughput: 0: 943.3. Samples: 378832. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:51:18,476][00219] Avg episode reward: [(0, '9.599')]
+[2023-02-25 18:51:19,180][12603] Updated weights for policy 0, policy_version 370 (0.0011)
+[2023-02-25 18:51:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1527808. Throughput: 0: 939.6. Samples: 381022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:51:23,475][00219] Avg episode reward: [(0, '9.597')]
+[2023-02-25 18:51:28,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1552384. Throughput: 0: 983.0. Samples: 387400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:51:28,476][00219] Avg episode reward: [(0, '10.448')]
+[2023-02-25 18:51:29,149][12603] Updated weights for policy 0, policy_version 380 (0.0026)
+[2023-02-25 18:51:33,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1572864. Throughput: 0: 980.5. Samples: 393750. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:51:33,481][00219] Avg episode reward: [(0, '11.195')]
+[2023-02-25 18:51:38,476][00219] Fps is (10 sec: 2866.6, 60 sec: 3754.5, 300 sec: 3790.5). Total num frames: 1581056. Throughput: 0: 940.9. Samples: 395412. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:51:38,479][00219] Avg episode reward: [(0, '11.437')]
+[2023-02-25 18:51:43,477][00219] Fps is (10 sec: 2047.2, 60 sec: 3686.2, 300 sec: 3776.6). Total num frames: 1593344. Throughput: 0: 893.4. Samples: 398840. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:51:43,480][00219] Avg episode reward: [(0, '11.771')]
+[2023-02-25 18:51:43,491][12589] Saving new best policy, reward=11.771!
+[2023-02-25 18:51:43,982][12603] Updated weights for policy 0, policy_version 390 (0.0020)
+[2023-02-25 18:51:48,474][00219] Fps is (10 sec: 2867.8, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 1609728. Throughput: 0: 900.3. Samples: 403706. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:51:48,479][00219] Avg episode reward: [(0, '11.580')]
+[2023-02-25 18:51:53,476][00219] Fps is (10 sec: 4096.6, 60 sec: 3618.0, 300 sec: 3762.7). Total num frames: 1634304. Throughput: 0: 901.4. Samples: 407240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:51:53,478][00219] Avg episode reward: [(0, '12.265')]
+[2023-02-25 18:51:53,499][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000399_1634304.pth...
+[2023-02-25 18:51:53,595][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000179_733184.pth
+[2023-02-25 18:51:53,610][12589] Saving new best policy, reward=12.265!
+[2023-02-25 18:51:53,945][12603] Updated weights for policy 0, policy_version 400 (0.0012)
+[2023-02-25 18:51:58,474][00219] Fps is (10 sec: 4505.3, 60 sec: 3686.4, 300 sec: 3776.6). Total num frames: 1654784. Throughput: 0: 888.6. Samples: 413874. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 18:51:58,477][00219] Avg episode reward: [(0, '13.951')]
+[2023-02-25 18:51:58,480][12589] Saving new best policy, reward=13.951!
+[2023-02-25 18:52:03,474][00219] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 1671168. Throughput: 0: 877.0. Samples: 418298. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:52:03,481][00219] Avg episode reward: [(0, '14.649')]
+[2023-02-25 18:52:03,490][12589] Saving new best policy, reward=14.649!
+[2023-02-25 18:52:06,234][12603] Updated weights for policy 0, policy_version 410 (0.0020)
+[2023-02-25 18:52:08,474][00219] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 1687552. Throughput: 0: 875.7. Samples: 420428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:52:08,476][00219] Avg episode reward: [(0, '14.893')]
+[2023-02-25 18:52:08,480][12589] Saving new best policy, reward=14.893!
+[2023-02-25 18:52:13,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 1708032. Throughput: 0: 883.9. Samples: 427174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:52:13,476][00219] Avg episode reward: [(0, '16.413')]
+[2023-02-25 18:52:13,485][12589] Saving new best policy, reward=16.413!
+[2023-02-25 18:52:15,359][12603] Updated weights for policy 0, policy_version 420 (0.0016)
+[2023-02-25 18:52:18,476][00219] Fps is (10 sec: 4095.2, 60 sec: 3618.0, 300 sec: 3776.7). Total num frames: 1728512. Throughput: 0: 880.4. Samples: 433368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:52:18,478][00219] Avg episode reward: [(0, '16.166')]
+[2023-02-25 18:52:23,478][00219] Fps is (10 sec: 3685.0, 60 sec: 3617.9, 300 sec: 3776.6). Total num frames: 1744896. Throughput: 0: 892.8. Samples: 435590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:52:23,485][00219] Avg episode reward: [(0, '15.296')]
+[2023-02-25 18:52:27,775][12603] Updated weights for policy 0, policy_version 430 (0.0017)
+[2023-02-25 18:52:28,474][00219] Fps is (10 sec: 3277.4, 60 sec: 3481.6, 300 sec: 3748.9). Total num frames: 1761280. Throughput: 0: 921.1. Samples: 440284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:52:28,479][00219] Avg episode reward: [(0, '16.563')]
+[2023-02-25 18:52:28,486][12589] Saving new best policy, reward=16.563!
+[2023-02-25 18:52:33,474][00219] Fps is (10 sec: 4097.6, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 1785856. Throughput: 0: 961.4. Samples: 446968. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:52:33,477][00219] Avg episode reward: [(0, '16.916')]
+[2023-02-25 18:52:33,493][12589] Saving new best policy, reward=16.916!
+[2023-02-25 18:52:37,191][12603] Updated weights for policy 0, policy_version 440 (0.0013)
+[2023-02-25 18:52:38,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3762.8). Total num frames: 1802240. Throughput: 0: 958.5. Samples: 450370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:52:38,475][00219] Avg episode reward: [(0, '17.059')]
+[2023-02-25 18:52:38,508][12589] Saving new best policy, reward=17.059!
+[2023-02-25 18:52:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3762.8). Total num frames: 1818624. Throughput: 0: 910.8. Samples: 454860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:52:43,476][00219] Avg episode reward: [(0, '16.595')]
+[2023-02-25 18:52:48,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1835008. Throughput: 0: 930.3. Samples: 460160. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:52:48,476][00219] Avg episode reward: [(0, '17.192')]
+[2023-02-25 18:52:48,504][12589] Saving new best policy, reward=17.192!
+[2023-02-25 18:52:49,382][12603] Updated weights for policy 0, policy_version 450 (0.0012)
+[2023-02-25 18:52:53,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3748.9). Total num frames: 1859584. Throughput: 0: 955.6. Samples: 463430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:52:53,476][00219] Avg episode reward: [(0, '17.036')]
+[2023-02-25 18:52:58,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1880064. Throughput: 0: 950.9. Samples: 469964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:52:58,479][00219] Avg episode reward: [(0, '17.476')]
+[2023-02-25 18:52:58,486][12589] Saving new best policy, reward=17.476!
+[2023-02-25 18:52:59,519][12603] Updated weights for policy 0, policy_version 460 (0.0014)
+[2023-02-25 18:53:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1892352. Throughput: 0: 911.0. Samples: 474362. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:03,479][00219] Avg episode reward: [(0, '17.885')]
+[2023-02-25 18:53:03,493][12589] Saving new best policy, reward=17.885!
+[2023-02-25 18:53:08,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1912832. Throughput: 0: 913.7. Samples: 476702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:08,480][00219] Avg episode reward: [(0, '19.489')]
+[2023-02-25 18:53:08,484][12589] Saving new best policy, reward=19.489!
+[2023-02-25 18:53:10,799][12603] Updated weights for policy 0, policy_version 470 (0.0033)
+[2023-02-25 18:53:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3749.0). Total num frames: 1937408. Throughput: 0: 965.1. Samples: 483714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:13,482][00219] Avg episode reward: [(0, '19.218')]
+[2023-02-25 18:53:18,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3762.8). Total num frames: 1953792. Throughput: 0: 953.9. Samples: 489892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:18,478][00219] Avg episode reward: [(0, '19.535')]
+[2023-02-25 18:53:18,593][12589] Saving new best policy, reward=19.535!
+[2023-02-25 18:53:21,307][12603] Updated weights for policy 0, policy_version 480 (0.0017)
+[2023-02-25 18:53:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3762.8). Total num frames: 1970176. Throughput: 0: 925.5. Samples: 492018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:53:23,478][00219] Avg episode reward: [(0, '19.995')]
+[2023-02-25 18:53:23,490][12589] Saving new best policy, reward=19.995!
+[2023-02-25 18:53:28,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1990656. Throughput: 0: 939.6. Samples: 497142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:28,478][00219] Avg episode reward: [(0, '19.973')]
+[2023-02-25 18:53:31,670][12603] Updated weights for policy 0, policy_version 490 (0.0027)
+[2023-02-25 18:53:33,474][00219] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2015232. Throughput: 0: 980.4. Samples: 504278. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:53:33,479][00219] Avg episode reward: [(0, '19.326')]
+[2023-02-25 18:53:38,475][00219] Fps is (10 sec: 4095.6, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 2031616. Throughput: 0: 982.3. Samples: 507634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:53:38,476][00219] Avg episode reward: [(0, '18.096')]
+[2023-02-25 18:53:42,783][12603] Updated weights for policy 0, policy_version 500 (0.0015)
+[2023-02-25 18:53:43,478][00219] Fps is (10 sec: 3275.6, 60 sec: 3822.7, 300 sec: 3762.7). Total num frames: 2048000. Throughput: 0: 937.9. Samples: 512172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:53:43,485][00219] Avg episode reward: [(0, '19.064')]
+[2023-02-25 18:53:48,474][00219] Fps is (10 sec: 3686.7, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 2068480. Throughput: 0: 966.2. Samples: 517840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:53:48,477][00219] Avg episode reward: [(0, '18.710')]
+[2023-02-25 18:53:53,474][00219] Fps is (10 sec: 3687.8, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2084864. Throughput: 0: 976.5. Samples: 520646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:53:53,477][00219] Avg episode reward: [(0, '18.964')]
+[2023-02-25 18:53:53,485][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth...
+[2023-02-25 18:53:53,629][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000291_1191936.pth
+[2023-02-25 18:53:54,305][12603] Updated weights for policy 0, policy_version 510 (0.0017)
+[2023-02-25 18:53:58,474][00219] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 2101248. Throughput: 0: 933.2. Samples: 525706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:53:58,476][00219] Avg episode reward: [(0, '19.222')]
+[2023-02-25 18:54:03,475][00219] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 2117632. Throughput: 0: 888.1. Samples: 529860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:54:03,479][00219] Avg episode reward: [(0, '19.820')]
+[2023-02-25 18:54:06,634][12603] Updated weights for policy 0, policy_version 520 (0.0034)
+[2023-02-25 18:54:08,481][00219] Fps is (10 sec: 3683.6, 60 sec: 3754.2, 300 sec: 3734.9). Total num frames: 2138112. Throughput: 0: 901.4. Samples: 532590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:54:08,486][00219] Avg episode reward: [(0, '19.205')]
+[2023-02-25 18:54:13,474][00219] Fps is (10 sec: 4096.7, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 2158592. Throughput: 0: 937.4. Samples: 539324. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:54:13,477][00219] Avg episode reward: [(0, '19.135')]
+[2023-02-25 18:54:16,242][12603] Updated weights for policy 0, policy_version 530 (0.0037)
+[2023-02-25 18:54:18,474][00219] Fps is (10 sec: 3689.2, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 2174976. Throughput: 0: 897.5. Samples: 544666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:54:18,480][00219] Avg episode reward: [(0, '20.032')]
+[2023-02-25 18:54:18,484][12589] Saving new best policy, reward=20.032!
+[2023-02-25 18:54:23,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2191360. Throughput: 0: 870.9. Samples: 546822. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:54:23,482][00219] Avg episode reward: [(0, '20.116')]
+[2023-02-25 18:54:23,496][12589] Saving new best policy, reward=20.116!
+[2023-02-25 18:54:28,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2207744. Throughput: 0: 885.5. Samples: 552016. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:54:28,479][00219] Avg episode reward: [(0, '19.392')]
+[2023-02-25 18:54:28,692][12603] Updated weights for policy 0, policy_version 540 (0.0023)
+[2023-02-25 18:54:33,474][00219] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 2232320. Throughput: 0: 909.7. Samples: 558778. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-25 18:54:33,476][00219] Avg episode reward: [(0, '19.379')]
+[2023-02-25 18:54:38,478][00219] Fps is (10 sec: 4094.4, 60 sec: 3618.0, 300 sec: 3734.9). Total num frames: 2248704. Throughput: 0: 908.0. Samples: 561510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:54:38,480][00219] Avg episode reward: [(0, '19.455')]
+[2023-02-25 18:54:39,344][12603] Updated weights for policy 0, policy_version 550 (0.0015)
+[2023-02-25 18:54:43,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3550.1, 300 sec: 3707.2). Total num frames: 2260992. Throughput: 0: 890.1. Samples: 565762. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:54:43,483][00219] Avg episode reward: [(0, '18.415')]
+[2023-02-25 18:54:48,474][00219] Fps is (10 sec: 3278.1, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 2281472. Throughput: 0: 924.7. Samples: 571468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:54:48,477][00219] Avg episode reward: [(0, '17.624')]
+[2023-02-25 18:54:50,577][12603] Updated weights for policy 0, policy_version 560 (0.0032)
+[2023-02-25 18:54:53,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2306048. Throughput: 0: 937.6. Samples: 574776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:54:53,482][00219] Avg episode reward: [(0, '17.612')]
+[2023-02-25 18:54:58,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2322432. Throughput: 0: 917.2. Samples: 580596. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:54:58,478][00219] Avg episode reward: [(0, '17.166')]
+[2023-02-25 18:55:02,617][12603] Updated weights for policy 0, policy_version 570 (0.0011)
+[2023-02-25 18:55:03,474][00219] Fps is (10 sec: 2867.1, 60 sec: 3618.2, 300 sec: 3693.3). Total num frames: 2334720. Throughput: 0: 891.1. Samples: 584766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:03,480][00219] Avg episode reward: [(0, '17.523')]
+[2023-02-25 18:55:08,474][00219] Fps is (10 sec: 3276.7, 60 sec: 3618.6, 300 sec: 3693.3). Total num frames: 2355200. Throughput: 0: 908.0. Samples: 587680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:55:08,481][00219] Avg episode reward: [(0, '16.939')]
+[2023-02-25 18:55:12,524][12603] Updated weights for policy 0, policy_version 580 (0.0015)
+[2023-02-25 18:55:13,474][00219] Fps is (10 sec: 4505.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2379776. Throughput: 0: 939.8. Samples: 594308. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:13,476][00219] Avg episode reward: [(0, '17.952')]
+[2023-02-25 18:55:18,479][00219] Fps is (10 sec: 4094.0, 60 sec: 3686.1, 300 sec: 3721.1). Total num frames: 2396160. Throughput: 0: 908.6. Samples: 599668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:18,481][00219] Avg episode reward: [(0, '18.257')]
+[2023-02-25 18:55:23,474][00219] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 2408448. Throughput: 0: 896.3. Samples: 601840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:23,485][00219] Avg episode reward: [(0, '18.382')]
+[2023-02-25 18:55:24,585][12603] Updated weights for policy 0, policy_version 590 (0.0023)
+[2023-02-25 18:55:28,474][00219] Fps is (10 sec: 3688.3, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2433024. Throughput: 0: 933.5. Samples: 607770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:28,481][00219] Avg episode reward: [(0, '19.485')]
+[2023-02-25 18:55:33,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2453504. Throughput: 0: 960.1. Samples: 614674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:55:33,480][00219] Avg episode reward: [(0, '19.699')]
+[2023-02-25 18:55:33,562][12603] Updated weights for policy 0, policy_version 600 (0.0025)
+[2023-02-25 18:55:38,477][00219] Fps is (10 sec: 3685.3, 60 sec: 3686.5, 300 sec: 3721.1). Total num frames: 2469888. Throughput: 0: 940.7. Samples: 617112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:55:38,481][00219] Avg episode reward: [(0, '19.506')]
+[2023-02-25 18:55:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2486272. Throughput: 0: 910.1. Samples: 621550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:43,480][00219] Avg episode reward: [(0, '21.298')]
+[2023-02-25 18:55:43,494][12589] Saving new best policy, reward=21.298!
+[2023-02-25 18:55:46,081][12603] Updated weights for policy 0, policy_version 610 (0.0013)
+[2023-02-25 18:55:48,474][00219] Fps is (10 sec: 3687.5, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2506752. Throughput: 0: 955.8. Samples: 627778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:48,480][00219] Avg episode reward: [(0, '21.309')]
+[2023-02-25 18:55:48,484][12589] Saving new best policy, reward=21.309!
+[2023-02-25 18:55:53,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2531328. Throughput: 0: 964.0. Samples: 631058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:55:53,479][00219] Avg episode reward: [(0, '20.129')]
+[2023-02-25 18:55:53,489][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000618_2531328.pth...
+[2023-02-25 18:55:53,597][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000399_1634304.pth
+[2023-02-25 18:55:56,046][12603] Updated weights for policy 0, policy_version 620 (0.0014)
+[2023-02-25 18:55:58,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2543616. Throughput: 0: 935.0. Samples: 636384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:55:58,476][00219] Avg episode reward: [(0, '19.630')]
+[2023-02-25 18:56:03,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2560000. Throughput: 0: 910.6. Samples: 640640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:03,481][00219] Avg episode reward: [(0, '20.189')]
+[2023-02-25 18:56:07,858][12603] Updated weights for policy 0, policy_version 630 (0.0037)
+[2023-02-25 18:56:08,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2580480. Throughput: 0: 932.3. Samples: 643792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:56:08,476][00219] Avg episode reward: [(0, '20.244')]
+[2023-02-25 18:56:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2605056. Throughput: 0: 953.5. Samples: 650676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:13,476][00219] Avg episode reward: [(0, '19.809')]
+[2023-02-25 18:56:18,476][00219] Fps is (10 sec: 3685.7, 60 sec: 3686.6, 300 sec: 3693.3). Total num frames: 2617344. Throughput: 0: 907.3. Samples: 655504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:18,480][00219] Avg episode reward: [(0, '19.027')]
+[2023-02-25 18:56:18,802][12603] Updated weights for policy 0, policy_version 640 (0.0013)
+[2023-02-25 18:56:23,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2633728. Throughput: 0: 899.7. Samples: 657596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:56:23,483][00219] Avg episode reward: [(0, '18.358')]
+[2023-02-25 18:56:28,474][00219] Fps is (10 sec: 3687.1, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2654208. Throughput: 0: 934.3. Samples: 663594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:28,476][00219] Avg episode reward: [(0, '17.866')]
+[2023-02-25 18:56:29,599][12603] Updated weights for policy 0, policy_version 650 (0.0014)
+[2023-02-25 18:56:33,474][00219] Fps is (10 sec: 4505.5, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2678784. Throughput: 0: 949.9. Samples: 670522. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:33,476][00219] Avg episode reward: [(0, '17.924')]
+[2023-02-25 18:56:38,475][00219] Fps is (10 sec: 3686.0, 60 sec: 3686.5, 300 sec: 3721.1). Total num frames: 2691072. Throughput: 0: 924.5. Samples: 672662. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:56:38,480][00219] Avg episode reward: [(0, '17.515')]
+[2023-02-25 18:56:42,090][12603] Updated weights for policy 0, policy_version 660 (0.0016)
+[2023-02-25 18:56:43,474][00219] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2703360. Throughput: 0: 890.2. Samples: 676444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:56:43,477][00219] Avg episode reward: [(0, '18.709')]
+[2023-02-25 18:56:48,474][00219] Fps is (10 sec: 2867.5, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2719744. Throughput: 0: 884.4. Samples: 680436. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:56:48,478][00219] Avg episode reward: [(0, '19.151')]
+[2023-02-25 18:56:53,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3665.6). Total num frames: 2736128. Throughput: 0: 867.3. Samples: 682822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:56:53,479][00219] Avg episode reward: [(0, '20.883')]
+[2023-02-25 18:56:54,703][12603] Updated weights for policy 0, policy_version 670 (0.0022)
+[2023-02-25 18:56:58,474][00219] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 2752512. Throughput: 0: 837.0. Samples: 688342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:56:58,477][00219] Avg episode reward: [(0, '21.594')]
+[2023-02-25 18:56:58,480][12589] Saving new best policy, reward=21.594!
+[2023-02-25 18:57:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 2768896. Throughput: 0: 824.8. Samples: 692618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:57:03,479][00219] Avg episode reward: [(0, '21.518')]
+[2023-02-25 18:57:07,392][12603] Updated weights for policy 0, policy_version 680 (0.0023)
+[2023-02-25 18:57:08,474][00219] Fps is (10 sec: 3686.6, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 2789376. Throughput: 0: 843.8. Samples: 695566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:08,482][00219] Avg episode reward: [(0, '21.042')]
+[2023-02-25 18:57:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 2813952. Throughput: 0: 865.2. Samples: 702526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:57:13,481][00219] Avg episode reward: [(0, '19.749')]
+[2023-02-25 18:57:17,308][12603] Updated weights for policy 0, policy_version 690 (0.0012)
+[2023-02-25 18:57:18,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3665.6). Total num frames: 2826240. Throughput: 0: 828.1. Samples: 707788. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:57:18,478][00219] Avg episode reward: [(0, '18.512')]
+[2023-02-25 18:57:23,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 2842624. Throughput: 0: 832.0. Samples: 710100. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:57:23,480][00219] Avg episode reward: [(0, '17.902')]
+[2023-02-25 18:57:28,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 2863104. Throughput: 0: 876.4. Samples: 715884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:28,481][00219] Avg episode reward: [(0, '18.349')]
+[2023-02-25 18:57:28,503][12603] Updated weights for policy 0, policy_version 700 (0.0014)
+[2023-02-25 18:57:33,474][00219] Fps is (10 sec: 4505.7, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 2887680. Throughput: 0: 948.1. Samples: 723102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:33,476][00219] Avg episode reward: [(0, '19.011')]
+[2023-02-25 18:57:38,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2904064. Throughput: 0: 953.0. Samples: 725706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:38,476][00219] Avg episode reward: [(0, '20.156')]
+[2023-02-25 18:57:39,078][12603] Updated weights for policy 0, policy_version 710 (0.0023)
+[2023-02-25 18:57:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2920448. Throughput: 0: 927.0. Samples: 730058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:43,476][00219] Avg episode reward: [(0, '19.614')]
+[2023-02-25 18:57:48,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2940928. Throughput: 0: 975.7. Samples: 736524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:57:48,489][00219] Avg episode reward: [(0, '21.317')]
+[2023-02-25 18:57:49,405][12603] Updated weights for policy 0, policy_version 720 (0.0014)
+[2023-02-25 18:57:53,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 2965504. Throughput: 0: 988.9. Samples: 740066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:57:53,476][00219] Avg episode reward: [(0, '21.147')]
+[2023-02-25 18:57:53,488][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000724_2965504.pth...
+[2023-02-25 18:57:53,622][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth
+[2023-02-25 18:57:58,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3693.3). Total num frames: 2981888. Throughput: 0: 955.1. Samples: 745506. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:57:58,477][00219] Avg episode reward: [(0, '20.580')]
+[2023-02-25 18:58:00,631][12603] Updated weights for policy 0, policy_version 730 (0.0017)
+[2023-02-25 18:58:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 2998272. Throughput: 0: 937.0. Samples: 749952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:58:03,481][00219] Avg episode reward: [(0, '19.930')]
+[2023-02-25 18:58:08,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3018752. Throughput: 0: 961.7. Samples: 753378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:58:08,476][00219] Avg episode reward: [(0, '21.482')]
+[2023-02-25 18:58:10,482][12603] Updated weights for policy 0, policy_version 740 (0.0014)
+[2023-02-25 18:58:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 3043328. Throughput: 0: 989.2. Samples: 760400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:58:13,482][00219] Avg episode reward: [(0, '20.444')]
+[2023-02-25 18:58:18,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3693.3). Total num frames: 3059712. Throughput: 0: 938.4. Samples: 765328. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:58:18,478][00219] Avg episode reward: [(0, '19.542')]
+[2023-02-25 18:58:22,368][12603] Updated weights for policy 0, policy_version 750 (0.0011)
+[2023-02-25 18:58:23,474][00219] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3072000. Throughput: 0: 929.2. Samples: 767522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:58:23,482][00219] Avg episode reward: [(0, '18.740')]
+[2023-02-25 18:58:28,474][00219] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3665.6). Total num frames: 3096576. Throughput: 0: 977.1. Samples: 774026. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:58:28,476][00219] Avg episode reward: [(0, '17.720')]
+[2023-02-25 18:58:31,253][12603] Updated weights for policy 0, policy_version 760 (0.0012)
+[2023-02-25 18:58:33,474][00219] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3693.4). Total num frames: 3121152. Throughput: 0: 988.2. Samples: 780992. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 18:58:33,484][00219] Avg episode reward: [(0, '17.991')]
+[2023-02-25 18:58:38,474][00219] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3133440. Throughput: 0: 959.4. Samples: 783240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 18:58:38,480][00219] Avg episode reward: [(0, '18.305')]
+[2023-02-25 18:58:43,334][12603] Updated weights for policy 0, policy_version 770 (0.0034)
+[2023-02-25 18:58:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3679.5). Total num frames: 3153920. Throughput: 0: 943.0. Samples: 787942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:58:43,476][00219] Avg episode reward: [(0, '19.331')]
+[2023-02-25 18:58:48,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3693.3). Total num frames: 3174400. Throughput: 0: 999.2. Samples: 794914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:58:48,483][00219] Avg episode reward: [(0, '18.602')]
+[2023-02-25 18:58:52,072][12603] Updated weights for policy 0, policy_version 780 (0.0018)
+[2023-02-25 18:58:53,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 3198976. Throughput: 0: 1001.6. Samples: 798448. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:58:53,476][00219] Avg episode reward: [(0, '18.692')]
+[2023-02-25 18:58:58,480][00219] Fps is (10 sec: 4093.4, 60 sec: 3890.8, 300 sec: 3721.1). Total num frames: 3215360. Throughput: 0: 958.9. Samples: 803556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:58:58,483][00219] Avg episode reward: [(0, '19.089')]
+[2023-02-25 18:59:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3707.3). Total num frames: 3231744. Throughput: 0: 962.5. Samples: 808642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:59:03,476][00219] Avg episode reward: [(0, '19.058')]
+[2023-02-25 18:59:04,032][12603] Updated weights for policy 0, policy_version 790 (0.0015)
+[2023-02-25 18:59:08,474][00219] Fps is (10 sec: 4098.5, 60 sec: 3959.5, 300 sec: 3721.1). Total num frames: 3256320. Throughput: 0: 995.5. Samples: 812318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:08,476][00219] Avg episode reward: [(0, '20.075')]
+[2023-02-25 18:59:12,559][12603] Updated weights for policy 0, policy_version 800 (0.0014)
+[2023-02-25 18:59:13,474][00219] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3276800. Throughput: 0: 1009.7. Samples: 819464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:13,482][00219] Avg episode reward: [(0, '21.817')]
+[2023-02-25 18:59:13,492][12589] Saving new best policy, reward=21.817!
+[2023-02-25 18:59:18,474][00219] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3293184. Throughput: 0: 952.7. Samples: 823864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:18,481][00219] Avg episode reward: [(0, '22.430')]
+[2023-02-25 18:59:18,482][12589] Saving new best policy, reward=22.430!
+[2023-02-25 18:59:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3735.0). Total num frames: 3309568. Throughput: 0: 952.7. Samples: 826110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:59:23,482][00219] Avg episode reward: [(0, '22.986')]
+[2023-02-25 18:59:23,492][12589] Saving new best policy, reward=22.986!
+[2023-02-25 18:59:25,016][12603] Updated weights for policy 0, policy_version 810 (0.0025)
+[2023-02-25 18:59:28,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3735.0). Total num frames: 3334144. Throughput: 0: 996.8. Samples: 832796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:28,482][00219] Avg episode reward: [(0, '22.808')]
+[2023-02-25 18:59:33,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3354624. Throughput: 0: 987.1. Samples: 839334. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 18:59:33,477][00219] Avg episode reward: [(0, '23.563')]
+[2023-02-25 18:59:33,491][12589] Saving new best policy, reward=23.563!
+[2023-02-25 18:59:34,660][12603] Updated weights for policy 0, policy_version 820 (0.0010)
+[2023-02-25 18:59:38,476][00219] Fps is (10 sec: 3276.1, 60 sec: 3891.1, 300 sec: 3748.9). Total num frames: 3366912. Throughput: 0: 957.7. Samples: 841548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 18:59:38,480][00219] Avg episode reward: [(0, '23.947')]
+[2023-02-25 18:59:38,489][12589] Saving new best policy, reward=23.947!
+[2023-02-25 18:59:43,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3387392. Throughput: 0: 949.8. Samples: 846290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:43,480][00219] Avg episode reward: [(0, '24.354')]
+[2023-02-25 18:59:43,489][12589] Saving new best policy, reward=24.354!
+[2023-02-25 18:59:45,938][12603] Updated weights for policy 0, policy_version 830 (0.0042)
+[2023-02-25 18:59:48,474][00219] Fps is (10 sec: 4096.8, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3407872. Throughput: 0: 989.7. Samples: 853178. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:48,476][00219] Avg episode reward: [(0, '24.667')]
+[2023-02-25 18:59:48,526][12589] Saving new best policy, reward=24.667!
+[2023-02-25 18:59:53,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3428352. Throughput: 0: 983.4. Samples: 856572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 18:59:53,480][00219] Avg episode reward: [(0, '25.174')]
+[2023-02-25 18:59:53,574][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000838_3432448.pth...
+[2023-02-25 18:59:53,715][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000618_2531328.pth
+[2023-02-25 18:59:53,731][12589] Saving new best policy, reward=25.174!
+[2023-02-25 18:59:56,498][12603] Updated weights for policy 0, policy_version 840 (0.0011)
+[2023-02-25 18:59:58,477][00219] Fps is (10 sec: 3685.3, 60 sec: 3823.1, 300 sec: 3762.7). Total num frames: 3444736. Throughput: 0: 928.6. Samples: 861252. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 18:59:58,479][00219] Avg episode reward: [(0, '24.451')]
+[2023-02-25 19:00:03,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3461120. Throughput: 0: 947.7. Samples: 866510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 19:00:03,476][00219] Avg episode reward: [(0, '24.150')]
+[2023-02-25 19:00:07,008][12603] Updated weights for policy 0, policy_version 850 (0.0011)
+[2023-02-25 19:00:08,474][00219] Fps is (10 sec: 4097.2, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3485696. Throughput: 0: 975.4. Samples: 870002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:00:08,478][00219] Avg episode reward: [(0, '24.074')]
+[2023-02-25 19:00:13,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3506176. Throughput: 0: 977.8. Samples: 876796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:00:13,479][00219] Avg episode reward: [(0, '23.062')]
+[2023-02-25 19:00:18,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3518464. Throughput: 0: 927.2. Samples: 881056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 19:00:18,477][00219] Avg episode reward: [(0, '24.495')]
+[2023-02-25 19:00:18,703][12603] Updated weights for policy 0, policy_version 860 (0.0013)
+[2023-02-25 19:00:23,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3538944. Throughput: 0: 926.7. Samples: 883246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:00:23,476][00219] Avg episode reward: [(0, '23.753')]
+[2023-02-25 19:00:28,462][12603] Updated weights for policy 0, policy_version 870 (0.0016)
+[2023-02-25 19:00:28,474][00219] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3563520. Throughput: 0: 973.6. Samples: 890104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 19:00:28,480][00219] Avg episode reward: [(0, '23.539')]
+[2023-02-25 19:00:33,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3579904. Throughput: 0: 957.7. Samples: 896276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:00:33,478][00219] Avg episode reward: [(0, '22.438')]
+[2023-02-25 19:00:38,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3762.8). Total num frames: 3596288. Throughput: 0: 932.3. Samples: 898524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 19:00:38,482][00219] Avg episode reward: [(0, '22.935')]
+[2023-02-25 19:00:40,517][12603] Updated weights for policy 0, policy_version 880 (0.0036)
+[2023-02-25 19:00:43,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3616768. Throughput: 0: 938.1. Samples: 903462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 19:00:43,480][00219] Avg episode reward: [(0, '21.341')]
+[2023-02-25 19:00:48,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3637248. Throughput: 0: 978.0. Samples: 910518. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 19:00:48,483][00219] Avg episode reward: [(0, '21.607')]
+[2023-02-25 19:00:49,524][12603] Updated weights for policy 0, policy_version 890 (0.0013)
+[2023-02-25 19:00:53,478][00219] Fps is (10 sec: 4094.2, 60 sec: 3822.7, 300 sec: 3776.6). Total num frames: 3657728. Throughput: 0: 978.7. Samples: 914050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 19:00:53,484][00219] Avg episode reward: [(0, '22.003')]
+[2023-02-25 19:00:58,476][00219] Fps is (10 sec: 3685.7, 60 sec: 3823.0, 300 sec: 3776.6). Total num frames: 3674112. Throughput: 0: 928.1. Samples: 918564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2023-02-25 19:00:58,479][00219] Avg episode reward: [(0, '22.499')]
+[2023-02-25 19:01:01,573][12603] Updated weights for policy 0, policy_version 900 (0.0027)
+[2023-02-25 19:01:03,474][00219] Fps is (10 sec: 3688.0, 60 sec: 3891.2, 300 sec: 3776.6). Total num frames: 3694592. Throughput: 0: 955.1. Samples: 924034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:01:03,477][00219] Avg episode reward: [(0, '21.666')]
+[2023-02-25 19:01:08,474][00219] Fps is (10 sec: 4096.8, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3715072. Throughput: 0: 984.8. Samples: 927560. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2023-02-25 19:01:08,476][00219] Avg episode reward: [(0, '22.608')]
+[2023-02-25 19:01:10,307][12603] Updated weights for policy 0, policy_version 910 (0.0017)
+[2023-02-25 19:01:13,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.6). Total num frames: 3735552. Throughput: 0: 980.3. Samples: 934218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 19:01:13,476][00219] Avg episode reward: [(0, '23.025')]
+[2023-02-25 19:01:18,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3751936. Throughput: 0: 939.5. Samples: 938552. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:01:18,477][00219] Avg episode reward: [(0, '23.578')]
+[2023-02-25 19:01:22,457][12603] Updated weights for policy 0, policy_version 920 (0.0026)
+[2023-02-25 19:01:23,474][00219] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3772416. Throughput: 0: 947.8. Samples: 941176. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 19:01:23,476][00219] Avg episode reward: [(0, '22.204')]
+[2023-02-25 19:01:28,474][00219] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3792896. Throughput: 0: 995.3. Samples: 948250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:01:28,476][00219] Avg episode reward: [(0, '22.208')]
+[2023-02-25 19:01:31,609][12603] Updated weights for policy 0, policy_version 930 (0.0016)
+[2023-02-25 19:01:33,474][00219] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3813376. Throughput: 0: 968.7. Samples: 954110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:01:33,476][00219] Avg episode reward: [(0, '22.848')]
+[2023-02-25 19:01:38,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3825664. Throughput: 0: 938.4. Samples: 956272. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-25 19:01:38,477][00219] Avg episode reward: [(0, '23.652')]
+[2023-02-25 19:01:43,468][12603] Updated weights for policy 0, policy_version 940 (0.0018)
+[2023-02-25 19:01:43,474][00219] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3850240. Throughput: 0: 959.9. Samples: 961758. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-25 19:01:43,476][00219] Avg episode reward: [(0, '22.696')]
+[2023-02-25 19:01:48,477][00219] Fps is (10 sec: 4094.8, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 3866624. Throughput: 0: 961.4. Samples: 967298. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2023-02-25 19:01:48,481][00219] Avg episode reward: [(0, '22.972')]
+[2023-02-25 19:01:53,479][00219] Fps is (10 sec: 2865.7, 60 sec: 3686.4, 300 sec: 3818.2). Total num frames: 3878912. Throughput: 0: 928.1. Samples: 969328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 19:01:53,481][00219] Avg episode reward: [(0, '23.154')]
+[2023-02-25 19:01:53,493][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000947_3878912.pth...
+[2023-02-25 19:01:53,706][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000724_2965504.pth
+[2023-02-25 19:01:57,939][12603] Updated weights for policy 0, policy_version 950 (0.0020)
+[2023-02-25 19:01:58,475][00219] Fps is (10 sec: 2458.0, 60 sec: 3618.2, 300 sec: 3804.4). Total num frames: 3891200. Throughput: 0: 859.0. Samples: 972874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:01:58,479][00219] Avg episode reward: [(0, '22.465')]
+[2023-02-25 19:02:03,474][00219] Fps is (10 sec: 2868.6, 60 sec: 3549.9, 300 sec: 3790.5). Total num frames: 3907584. Throughput: 0: 872.0. Samples: 977794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:02:03,476][00219] Avg episode reward: [(0, '23.118')]
+[2023-02-25 19:02:08,374][12603] Updated weights for policy 0, policy_version 960 (0.0013)
+[2023-02-25 19:02:08,474][00219] Fps is (10 sec: 4096.5, 60 sec: 3618.1, 300 sec: 3790.5). Total num frames: 3932160. Throughput: 0: 888.4. Samples: 981154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:02:08,483][00219] Avg episode reward: [(0, '22.579')]
+[2023-02-25 19:02:13,474][00219] Fps is (10 sec: 4505.4, 60 sec: 3618.1, 300 sec: 3818.3). Total num frames: 3952640. Throughput: 0: 881.9. Samples: 987934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-25 19:02:13,480][00219] Avg episode reward: [(0, '24.567')]
+[2023-02-25 19:02:18,474][00219] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3804.4). Total num frames: 3964928. Throughput: 0: 844.8. Samples: 992126. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2023-02-25 19:02:18,478][00219] Avg episode reward: [(0, '24.035')]
+[2023-02-25 19:02:20,584][12603] Updated weights for policy 0, policy_version 970 (0.0020)
+[2023-02-25 19:02:23,474][00219] Fps is (10 sec: 2867.4, 60 sec: 3481.6, 300 sec: 3790.5). Total num frames: 3981312. Throughput: 0: 845.7. Samples: 994330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2023-02-25 19:02:23,476][00219] Avg episode reward: [(0, '24.706')]
+[2023-02-25 19:02:28,289][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-25 19:02:28,289][00219] Component Batcher_0 stopped!
+[2023-02-25 19:02:28,290][12589] Stopping Batcher_0...
+[2023-02-25 19:02:28,304][12589] Loop batcher_evt_loop terminating...
+[2023-02-25 19:02:28,336][12603] Weights refcount: 2 0
+[2023-02-25 19:02:28,355][00219] Component InferenceWorker_p0-w0 stopped!
+[2023-02-25 19:02:28,357][12603] Stopping InferenceWorker_p0-w0...
+[2023-02-25 19:02:28,358][12603] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-25 19:02:28,363][00219] Component RolloutWorker_w7 stopped!
+[2023-02-25 19:02:28,362][12611] Stopping RolloutWorker_w7...
+[2023-02-25 19:02:28,377][12611] Loop rollout_proc7_evt_loop terminating...
+[2023-02-25 19:02:28,390][00219] Component RolloutWorker_w0 stopped!
+[2023-02-25 19:02:28,393][12604] Stopping RolloutWorker_w0...
+[2023-02-25 19:02:28,393][12604] Loop rollout_proc0_evt_loop terminating...
+[2023-02-25 19:02:28,395][00219] Component RolloutWorker_w5 stopped!
+[2023-02-25 19:02:28,397][00219] Component RolloutWorker_w4 stopped!
+[2023-02-25 19:02:28,395][12609] Stopping RolloutWorker_w5...
+[2023-02-25 19:02:28,400][12609] Loop rollout_proc5_evt_loop terminating...
+[2023-02-25 19:02:28,403][12606] Stopping RolloutWorker_w2...
+[2023-02-25 19:02:28,403][12606] Loop rollout_proc2_evt_loop terminating...
+[2023-02-25 19:02:28,395][12607] Stopping RolloutWorker_w4...
+[2023-02-25 19:02:28,405][12607] Loop rollout_proc4_evt_loop terminating...
+[2023-02-25 19:02:28,397][12605] Stopping RolloutWorker_w1...
+[2023-02-25 19:02:28,398][00219] Component RolloutWorker_w3 stopped!
+[2023-02-25 19:02:28,407][00219] Component RolloutWorker_w1 stopped!
+[2023-02-25 19:02:28,396][12608] Stopping RolloutWorker_w3...
+[2023-02-25 19:02:28,408][00219] Component RolloutWorker_w2 stopped!
+[2023-02-25 19:02:28,412][12608] Loop rollout_proc3_evt_loop terminating...
+[2023-02-25 19:02:28,406][12605] Loop rollout_proc1_evt_loop terminating...
+[2023-02-25 19:02:28,431][00219] Component RolloutWorker_w6 stopped!
+[2023-02-25 19:02:28,433][12610] Stopping RolloutWorker_w6...
+[2023-02-25 19:02:28,437][12610] Loop rollout_proc6_evt_loop terminating...
+[2023-02-25 19:02:28,486][12589] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000838_3432448.pth
+[2023-02-25 19:02:28,504][12589] Saving new best policy, reward=26.052!
+[2023-02-25 19:02:28,676][12589] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-25 19:02:28,864][00219] Component LearnerWorker_p0 stopped!
+[2023-02-25 19:02:28,866][00219] Waiting for process learner_proc0 to stop...
+[2023-02-25 19:02:28,869][12589] Stopping LearnerWorker_p0...
+[2023-02-25 19:02:28,869][12589] Loop learner_proc0_evt_loop terminating...
+[2023-02-25 19:02:30,632][00219] Waiting for process inference_proc0-0 to join...
+[2023-02-25 19:02:30,938][00219] Waiting for process rollout_proc0 to join...
+[2023-02-25 19:02:31,333][00219] Waiting for process rollout_proc1 to join...
+[2023-02-25 19:02:31,335][00219] Waiting for process rollout_proc2 to join...
+[2023-02-25 19:02:31,338][00219] Waiting for process rollout_proc3 to join...
+[2023-02-25 19:02:31,339][00219] Waiting for process rollout_proc4 to join...
+[2023-02-25 19:02:31,340][00219] Waiting for process rollout_proc5 to join...
+[2023-02-25 19:02:31,341][00219] Waiting for process rollout_proc6 to join...
+[2023-02-25 19:02:31,342][00219] Waiting for process rollout_proc7 to join...
+[2023-02-25 19:02:31,343][00219] Batcher 0 profile tree view:
+batching: 25.2117, releasing_batches: 0.0278
+[2023-02-25 19:02:31,345][00219] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 548.8303
+update_model: 7.2818
+  weight_update: 0.0017
+one_step: 0.0024
+  handle_policy_step: 490.4408
+    deserialize: 14.9426, stack: 2.8507, obs_to_device_normalize: 110.6946, forward: 233.2077, send_messages: 25.8023
+    prepare_outputs: 78.1920
+      to_cpu: 48.4714
+[2023-02-25 19:02:31,346][00219] Learner 0 profile tree view:
+misc: 0.0104, prepare_batch: 16.6086
+train: 74.9911
+  epoch_init: 0.0180, minibatch_init: 0.0099, losses_postprocess: 0.6100, kl_divergence: 0.5355, after_optimizer: 33.3823
+  calculate_losses: 26.2628
+    losses_init: 0.0132, forward_head: 1.6609, bptt_initial: 17.5531, tail: 1.0730, advantages_returns: 0.2530, losses: 3.3578
+    bptt: 2.0744
+      bptt_forward_core: 1.9836
+  update: 13.5598
+    clip: 1.3489
+[2023-02-25 19:02:31,347][00219] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.3330, enqueue_policy_requests: 152.1954, env_step: 809.3310, overhead: 20.9125, complete_rollouts: 6.1680
+save_policy_outputs: 19.7973
+  split_output_tensors: 9.6528
+[2023-02-25 19:02:31,348][00219] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.2955, enqueue_policy_requests: 153.3418, env_step: 808.5985, overhead: 20.5743, complete_rollouts: 7.3208
+save_policy_outputs: 19.7544
+  split_output_tensors: 9.7981
+[2023-02-25 19:02:31,350][00219] Loop Runner_EvtLoop terminating...
+[2023-02-25 19:02:31,351][00219] Runner profile tree view:
+main_loop: 1113.1394
+[2023-02-25 19:02:31,352][00219] Collected {0: 4005888}, FPS: 3598.7
+[2023-02-25 19:19:55,934][00219] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-25 19:19:55,935][00219] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-25 19:19:55,938][00219] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-25 19:19:55,941][00219] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-25 19:19:55,945][00219] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 19:19:55,947][00219] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-25 19:19:55,949][00219] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 19:19:55,954][00219] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-25 19:19:55,956][00219] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-02-25 19:19:55,959][00219] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-02-25 19:19:55,960][00219] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-25 19:19:55,962][00219] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-25 19:19:55,963][00219] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-25 19:19:55,965][00219] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-25 19:19:55,967][00219] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-25 19:19:55,989][00219] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-25 19:19:55,992][00219] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 19:19:55,996][00219] RunningMeanStd input shape: (1,)
+[2023-02-25 19:19:56,013][00219] ConvEncoder: input_channels=3
+[2023-02-25 19:19:56,665][00219] Conv encoder output size: 512
+[2023-02-25 19:19:56,667][00219] Policy head output size: 512
+[2023-02-25 19:19:59,027][00219] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-25 19:20:00,254][00219] Num frames 100...
+[2023-02-25 19:20:00,369][00219] Num frames 200...
+[2023-02-25 19:20:00,478][00219] Num frames 300...
+[2023-02-25 19:20:00,592][00219] Num frames 400...
+[2023-02-25 19:20:00,714][00219] Num frames 500...
+[2023-02-25 19:20:00,835][00219] Num frames 600...
+[2023-02-25 19:20:00,951][00219] Num frames 700...
+[2023-02-25 19:20:01,058][00219] Num frames 800...
+[2023-02-25 19:20:01,172][00219] Num frames 900...
+[2023-02-25 19:20:01,317][00219] Avg episode rewards: #0: 23.770, true rewards: #0: 9.770
+[2023-02-25 19:20:01,319][00219] Avg episode reward: 23.770, avg true_objective: 9.770
+[2023-02-25 19:20:01,350][00219] Num frames 1000...
+[2023-02-25 19:20:01,460][00219] Num frames 1100...
+[2023-02-25 19:20:01,567][00219] Num frames 1200...
+[2023-02-25 19:20:01,682][00219] Num frames 1300...
+[2023-02-25 19:20:01,791][00219] Num frames 1400...
+[2023-02-25 19:20:01,906][00219] Num frames 1500...
+[2023-02-25 19:20:02,020][00219] Num frames 1600...
+[2023-02-25 19:20:02,129][00219] Num frames 1700...
+[2023-02-25 19:20:02,207][00219] Avg episode rewards: #0: 19.065, true rewards: #0: 8.565
+[2023-02-25 19:20:02,209][00219] Avg episode reward: 19.065, avg true_objective: 8.565
+[2023-02-25 19:20:02,306][00219] Num frames 1800...
+[2023-02-25 19:20:02,415][00219] Num frames 1900...
+[2023-02-25 19:20:02,531][00219] Num frames 2000...
+[2023-02-25 19:20:02,642][00219] Num frames 2100...
+[2023-02-25 19:20:02,756][00219] Num frames 2200...
+[2023-02-25 19:20:02,864][00219] Num frames 2300...
+[2023-02-25 19:20:02,979][00219] Num frames 2400...
+[2023-02-25 19:20:03,096][00219] Num frames 2500...
+[2023-02-25 19:20:03,205][00219] Num frames 2600...
+[2023-02-25 19:20:03,321][00219] Num frames 2700...
+[2023-02-25 19:20:03,432][00219] Num frames 2800...
+[2023-02-25 19:20:03,548][00219] Avg episode rewards: #0: 22.110, true rewards: #0: 9.443
+[2023-02-25 19:20:03,551][00219] Avg episode reward: 22.110, avg true_objective: 9.443
+[2023-02-25 19:20:03,655][00219] Num frames 2900...
+[2023-02-25 19:20:03,812][00219] Num frames 3000...
+[2023-02-25 19:20:03,967][00219] Num frames 3100...
+[2023-02-25 19:20:04,122][00219] Num frames 3200...
+[2023-02-25 19:20:04,277][00219] Num frames 3300...
+[2023-02-25 19:20:04,441][00219] Num frames 3400...
+[2023-02-25 19:20:04,608][00219] Num frames 3500...
+[2023-02-25 19:20:04,761][00219] Num frames 3600...
+[2023-02-25 19:20:04,915][00219] Num frames 3700...
+[2023-02-25 19:20:05,071][00219] Num frames 3800...
+[2023-02-25 19:20:05,234][00219] Num frames 3900...
+[2023-02-25 19:20:05,384][00219] Num frames 4000...
+[2023-02-25 19:20:05,542][00219] Num frames 4100...
+[2023-02-25 19:20:05,726][00219] Num frames 4200...
+[2023-02-25 19:20:05,902][00219] Num frames 4300...
+[2023-02-25 19:20:06,076][00219] Num frames 4400...
+[2023-02-25 19:20:06,245][00219] Num frames 4500...
+[2023-02-25 19:20:06,452][00219] Avg episode rewards: #0: 29.732, true rewards: #0: 11.482
+[2023-02-25 19:20:06,454][00219] Avg episode reward: 29.732, avg true_objective: 11.482
+[2023-02-25 19:20:06,466][00219] Num frames 4600...
+[2023-02-25 19:20:06,625][00219] Num frames 4700...
+[2023-02-25 19:20:06,789][00219] Num frames 4800...
+[2023-02-25 19:20:06,953][00219] Num frames 4900...
+[2023-02-25 19:20:07,079][00219] Num frames 5000...
+[2023-02-25 19:20:07,188][00219] Num frames 5100...
+[2023-02-25 19:20:07,306][00219] Num frames 5200...
+[2023-02-25 19:20:07,470][00219] Avg episode rewards: #0: 26.394, true rewards: #0: 10.594
+[2023-02-25 19:20:07,471][00219] Avg episode reward: 26.394, avg true_objective: 10.594
+[2023-02-25 19:20:07,479][00219] Num frames 5300...
+[2023-02-25 19:20:07,589][00219] Num frames 5400...
+[2023-02-25 19:20:07,700][00219] Num frames 5500...
+[2023-02-25 19:20:07,811][00219] Num frames 5600...
+[2023-02-25 19:20:07,929][00219] Num frames 5700...
+[2023-02-25 19:20:08,040][00219] Num frames 5800...
+[2023-02-25 19:20:08,155][00219] Num frames 5900...
+[2023-02-25 19:20:08,273][00219] Num frames 6000...
+[2023-02-25 19:20:08,384][00219] Num frames 6100...
+[2023-02-25 19:20:08,503][00219] Num frames 6200...
+[2023-02-25 19:20:08,613][00219] Num frames 6300...
+[2023-02-25 19:20:08,729][00219] Num frames 6400...
+[2023-02-25 19:20:08,841][00219] Num frames 6500...
+[2023-02-25 19:20:08,953][00219] Num frames 6600...
+[2023-02-25 19:20:09,073][00219] Num frames 6700...
+[2023-02-25 19:20:09,186][00219] Num frames 6800...
+[2023-02-25 19:20:09,300][00219] Num frames 6900...
+[2023-02-25 19:20:09,412][00219] Num frames 7000...
+[2023-02-25 19:20:09,581][00219] Avg episode rewards: #0: 30.165, true rewards: #0: 11.832
+[2023-02-25 19:20:09,582][00219] Avg episode reward: 30.165, avg true_objective: 11.832
+[2023-02-25 19:20:09,588][00219] Num frames 7100...
+[2023-02-25 19:20:09,697][00219] Num frames 7200...
+[2023-02-25 19:20:09,809][00219] Num frames 7300...
+[2023-02-25 19:20:09,920][00219] Num frames 7400...
+[2023-02-25 19:20:10,033][00219] Num frames 7500...
+[2023-02-25 19:20:10,151][00219] Num frames 7600...
+[2023-02-25 19:20:10,259][00219] Num frames 7700...
+[2023-02-25 19:20:10,368][00219] Num frames 7800...
+[2023-02-25 19:20:10,429][00219] Avg episode rewards: #0: 28.004, true rewards: #0: 11.147
+[2023-02-25 19:20:10,431][00219] Avg episode reward: 28.004, avg true_objective: 11.147
+[2023-02-25 19:20:10,538][00219] Num frames 7900...
+[2023-02-25 19:20:10,650][00219] Num frames 8000...
+[2023-02-25 19:20:10,758][00219] Num frames 8100...
+[2023-02-25 19:20:10,868][00219] Num frames 8200...
+[2023-02-25 19:20:11,018][00219] Avg episode rewards: #0: 25.354, true rewards: #0: 10.354
+[2023-02-25 19:20:11,019][00219] Avg episode reward: 25.354, avg true_objective: 10.354
+[2023-02-25 19:20:11,041][00219] Num frames 8300...
+[2023-02-25 19:20:11,169][00219] Num frames 8400...
+[2023-02-25 19:20:11,284][00219] Num frames 8500...
+[2023-02-25 19:20:11,393][00219] Num frames 8600...
+[2023-02-25 19:20:11,507][00219] Num frames 8700...
+[2023-02-25 19:20:11,616][00219] Num frames 8800...
+[2023-02-25 19:20:11,745][00219] Num frames 8900...
+[2023-02-25 19:20:11,855][00219] Num frames 9000...
+[2023-02-25 19:20:11,963][00219] Num frames 9100...
+[2023-02-25 19:20:12,081][00219] Num frames 9200...
+[2023-02-25 19:20:12,195][00219] Num frames 9300...
+[2023-02-25 19:20:12,306][00219] Num frames 9400...
+[2023-02-25 19:20:12,417][00219] Num frames 9500...
+[2023-02-25 19:20:12,491][00219] Avg episode rewards: #0: 26.239, true rewards: #0: 10.572
+[2023-02-25 19:20:12,493][00219] Avg episode reward: 26.239, avg true_objective: 10.572
+[2023-02-25 19:20:12,589][00219] Num frames 9600...
+[2023-02-25 19:20:12,699][00219] Num frames 9700...
+[2023-02-25 19:20:12,810][00219] Num frames 9800...
+[2023-02-25 19:20:12,921][00219] Num frames 9900...
+[2023-02-25 19:20:13,041][00219] Num frames 10000...
+[2023-02-25 19:20:13,156][00219] Num frames 10100...
+[2023-02-25 19:20:13,273][00219] Num frames 10200...
+[2023-02-25 19:20:13,389][00219] Num frames 10300...
+[2023-02-25 19:20:13,501][00219] Num frames 10400...
+[2023-02-25 19:20:13,611][00219] Num frames 10500...
+[2023-02-25 19:20:13,727][00219] Num frames 10600...
+[2023-02-25 19:20:13,835][00219] Num frames 10700...
+[2023-02-25 19:20:13,951][00219] Num frames 10800...
+[2023-02-25 19:20:14,060][00219] Num frames 10900...
+[2023-02-25 19:20:14,177][00219] Num frames 11000...
+[2023-02-25 19:20:14,296][00219] Num frames 11100...
+[2023-02-25 19:20:14,407][00219] Num frames 11200...
+[2023-02-25 19:20:14,524][00219] Num frames 11300...
+[2023-02-25 19:20:14,634][00219] Num frames 11400...
+[2023-02-25 19:20:14,750][00219] Num frames 11500...
+[2023-02-25 19:20:14,862][00219] Num frames 11600...
+[2023-02-25 19:20:14,937][00219] Avg episode rewards: #0: 29.315, true rewards: #0: 11.615
+[2023-02-25 19:20:14,938][00219] Avg episode reward: 29.315, avg true_objective: 11.615
+[2023-02-25 19:21:22,320][00219] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-02-25 19:23:11,077][00219] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-25 19:23:11,079][00219] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-25 19:23:11,081][00219] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-25 19:23:11,082][00219] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-25 19:23:11,084][00219] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 19:23:11,085][00219] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-25 19:23:11,087][00219] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-25 19:23:11,088][00219] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-25 19:23:11,089][00219] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-25 19:23:11,091][00219] Adding new argument 'hf_repository'='ThomasSimonini/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-25 19:23:11,092][00219] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-25 19:23:11,094][00219] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-25 19:23:11,095][00219] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-25 19:23:11,096][00219] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-25 19:23:11,098][00219] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-25 19:23:11,128][00219] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 19:23:11,130][00219] RunningMeanStd input shape: (1,)
+[2023-02-25 19:23:11,144][00219] ConvEncoder: input_channels=3
+[2023-02-25 19:23:11,179][00219] Conv encoder output size: 512
+[2023-02-25 19:23:11,180][00219] Policy head output size: 512
+[2023-02-25 19:23:11,201][00219] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-25 19:23:11,643][00219] Num frames 100...
+[2023-02-25 19:23:11,759][00219] Num frames 200...
+[2023-02-25 19:23:11,872][00219] Num frames 300...
+[2023-02-25 19:23:12,002][00219] Num frames 400...
+[2023-02-25 19:23:12,118][00219] Num frames 500...
+[2023-02-25 19:23:12,233][00219] Num frames 600...
+[2023-02-25 19:23:12,348][00219] Num frames 700...
+[2023-02-25 19:23:12,455][00219] Num frames 800...
+[2023-02-25 19:23:12,574][00219] Num frames 900...
+[2023-02-25 19:23:12,680][00219] Num frames 1000...
+[2023-02-25 19:23:12,761][00219] Avg episode rewards: #0: 20.240, true rewards: #0: 10.240
+[2023-02-25 19:23:12,762][00219] Avg episode reward: 20.240, avg true_objective: 10.240
+[2023-02-25 19:23:12,849][00219] Num frames 1100...
+[2023-02-25 19:23:12,964][00219] Num frames 1200...
+[2023-02-25 19:23:13,080][00219] Num frames 1300...
+[2023-02-25 19:23:13,190][00219] Num frames 1400...
+[2023-02-25 19:23:13,318][00219] Num frames 1500...
+[2023-02-25 19:23:13,430][00219] Num frames 1600...
+[2023-02-25 19:23:13,482][00219] Avg episode rewards: #0: 15.000, true rewards: #0: 8.000
+[2023-02-25 19:23:13,484][00219] Avg episode reward: 15.000, avg true_objective: 8.000
+[2023-02-25 19:23:13,601][00219] Num frames 1700...
+[2023-02-25 19:23:13,712][00219] Num frames 1800...
+[2023-02-25 19:23:13,819][00219] Num frames 1900...
+[2023-02-25 19:23:13,929][00219] Num frames 2000...
+[2023-02-25 19:23:14,054][00219] Num frames 2100...
+[2023-02-25 19:23:14,165][00219] Num frames 2200...
+[2023-02-25 19:23:14,277][00219] Num frames 2300...
+[2023-02-25 19:23:14,396][00219] Num frames 2400...
+[2023-02-25 19:23:14,507][00219] Num frames 2500...
+[2023-02-25 19:23:14,639][00219] Num frames 2600...
+[2023-02-25 19:23:14,758][00219] Num frames 2700...
+[2023-02-25 19:23:14,875][00219] Num frames 2800...
+[2023-02-25 19:23:14,986][00219] Num frames 2900...
+[2023-02-25 19:23:15,096][00219] Num frames 3000...
+[2023-02-25 19:23:15,216][00219] Num frames 3100...
+[2023-02-25 19:23:15,330][00219] Num frames 3200...
+[2023-02-25 19:23:15,450][00219] Num frames 3300...
+[2023-02-25 19:23:15,565][00219] Num frames 3400...
+[2023-02-25 19:23:15,677][00219] Num frames 3500...
+[2023-02-25 19:23:15,829][00219] Avg episode rewards: #0: 26.280, true rewards: #0: 11.947
+[2023-02-25 19:23:15,831][00219] Avg episode reward: 26.280, avg true_objective: 11.947
+[2023-02-25 19:23:15,853][00219] Num frames 3600...
+[2023-02-25 19:23:15,963][00219] Num frames 3700...
+[2023-02-25 19:23:16,074][00219] Num frames 3800...
+[2023-02-25 19:23:16,189][00219] Num frames 3900...
+[2023-02-25 19:23:16,306][00219] Num frames 4000...
+[2023-02-25 19:23:16,416][00219] Num frames 4100...
+[2023-02-25 19:23:16,529][00219] Num frames 4200...
+[2023-02-25 19:23:16,650][00219] Num frames 4300...
+[2023-02-25 19:23:16,772][00219] Num frames 4400...
+[2023-02-25 19:23:16,889][00219] Num frames 4500...
+[2023-02-25 19:23:16,999][00219] Num frames 4600...
+[2023-02-25 19:23:17,116][00219] Num frames 4700...
+[2023-02-25 19:23:17,228][00219] Num frames 4800...
+[2023-02-25 19:23:17,351][00219] Num frames 4900...
+[2023-02-25 19:23:17,470][00219] Num frames 5000...
+[2023-02-25 19:23:17,626][00219] Num frames 5100...
+[2023-02-25 19:23:17,742][00219] Num frames 5200...
+[2023-02-25 19:23:17,957][00219] Num frames 5300...
+[2023-02-25 19:23:18,122][00219] Num frames 5400...
+[2023-02-25 19:23:18,243][00219] Num frames 5500...
+[2023-02-25 19:23:18,344][00219] Avg episode rewards: #0: 33.100, true rewards: #0: 13.850
+[2023-02-25 19:23:18,345][00219] Avg episode reward: 33.100, avg true_objective: 13.850
+[2023-02-25 19:23:18,414][00219] Num frames 5600...
+[2023-02-25 19:23:18,633][00219] Num frames 5700...
+[2023-02-25 19:23:18,789][00219] Num frames 5800...
+[2023-02-25 19:23:18,975][00219] Num frames 5900...
+[2023-02-25 19:23:19,172][00219] Num frames 6000...
+[2023-02-25 19:23:19,328][00219] Num frames 6100...
+[2023-02-25 19:23:19,700][00219] Num frames 6200...
+[2023-02-25 19:23:20,135][00219] Num frames 6300...
+[2023-02-25 19:23:24,140][00219] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-25 19:23:24,142][00219] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-25 19:23:24,144][00219] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-25 19:23:24,146][00219] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-25 19:23:24,149][00219] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-25 19:23:24,150][00219] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-25 19:23:24,155][00219] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-25 19:23:24,156][00219] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-25 19:23:24,158][00219] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-25 19:23:24,159][00219] Adding new argument 'hf_repository'='msgerasyov/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-25 19:23:24,164][00219] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-25 19:23:24,165][00219] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-25 19:23:24,167][00219] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-25 19:23:24,168][00219] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-25 19:23:24,169][00219] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-25 19:23:24,193][00219] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-25 19:23:24,195][00219] RunningMeanStd input shape: (1,)
+[2023-02-25 19:23:24,208][00219] ConvEncoder: input_channels=3
+[2023-02-25 19:23:24,244][00219] Conv encoder output size: 512
+[2023-02-25 19:23:24,245][00219] Policy head output size: 512
+[2023-02-25 19:23:24,267][00219] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-25 19:23:24,701][00219] Num frames 100...
+[2023-02-25 19:23:24,821][00219] Num frames 200...
+[2023-02-25 19:23:24,938][00219] Num frames 300...
+[2023-02-25 19:23:25,054][00219] Num frames 400...
+[2023-02-25 19:23:25,170][00219] Num frames 500...
+[2023-02-25 19:23:25,280][00219] Avg episode rewards: #0: 8.470, true rewards: #0: 5.470
+[2023-02-25 19:23:25,281][00219] Avg episode reward: 8.470, avg true_objective: 5.470
+[2023-02-25 19:23:25,346][00219] Num frames 600...
+[2023-02-25 19:23:25,459][00219] Num frames 700...
+[2023-02-25 19:23:25,571][00219] Num frames 800...
+[2023-02-25 19:23:25,683][00219] Num frames 900...
+[2023-02-25 19:23:25,801][00219] Num frames 1000...
+[2023-02-25 19:23:25,917][00219] Num frames 1100...
+[2023-02-25 19:23:26,032][00219] Num frames 1200...
+[2023-02-25 19:23:26,150][00219] Num frames 1300...
+[2023-02-25 19:23:26,265][00219] Avg episode rewards: #0: 12.770, true rewards: #0: 6.770
+[2023-02-25 19:23:26,266][00219] Avg episode reward: 12.770, avg true_objective: 6.770
+[2023-02-25 19:23:26,320][00219] Num frames 1400...
+[2023-02-25 19:23:26,437][00219] Num frames 1500...
+[2023-02-25 19:23:26,547][00219] Num frames 1600...
+[2023-02-25 19:23:26,658][00219] Num frames 1700...
+[2023-02-25 19:23:26,780][00219] Num frames 1800...
+[2023-02-25 19:23:26,891][00219] Num frames 1900...
+[2023-02-25 19:23:27,004][00219] Num frames 2000...
+[2023-02-25 19:23:27,131][00219] Num frames 2100...
+[2023-02-25 19:23:27,245][00219] Num frames 2200...
+[2023-02-25 19:23:27,358][00219] Num frames 2300...
+[2023-02-25 19:23:27,478][00219] Num frames 2400...
+[2023-02-25 19:23:27,589][00219] Num frames 2500...
+[2023-02-25 19:23:27,698][00219] Num frames 2600...
+[2023-02-25 19:23:27,823][00219] Num frames 2700...
+[2023-02-25 19:23:27,939][00219] Num frames 2800...
+[2023-02-25 19:23:28,057][00219] Num frames 2900...
+[2023-02-25 19:23:28,174][00219] Num frames 3000...
+[2023-02-25 19:23:28,286][00219] Num frames 3100...
+[2023-02-25 19:23:28,398][00219] Num frames 3200...
+[2023-02-25 19:23:28,512][00219] Num frames 3300...
+[2023-02-25 19:23:28,622][00219] Num frames 3400...
+[2023-02-25 19:23:28,737][00219] Avg episode rewards: #0: 28.180, true rewards: #0: 11.513
+[2023-02-25 19:23:28,740][00219] Avg episode reward: 28.180, avg true_objective: 11.513
+[2023-02-25 19:23:28,804][00219] Num frames 3500...
+[2023-02-25 19:23:28,912][00219] Num frames 3600...
+[2023-02-25 19:23:29,026][00219] Num frames 3700...
+[2023-02-25 19:23:29,142][00219] Num frames 3800...
+[2023-02-25 19:23:29,253][00219] Num frames 3900...
+[2023-02-25 19:23:29,368][00219] Num frames 4000...
+[2023-02-25 19:23:29,483][00219] Num frames 4100...
+[2023-02-25 19:23:29,552][00219] Avg episode rewards: #0: 23.780, true rewards: #0: 10.280
+[2023-02-25 19:23:29,554][00219] Avg episode reward: 23.780, avg true_objective: 10.280
+[2023-02-25 19:23:29,656][00219] Num frames 4200...
+[2023-02-25 19:23:29,766][00219] Num frames 4300...
+[2023-02-25 19:23:29,887][00219] Num frames 4400...
+[2023-02-25 19:23:30,003][00219] Num frames 4500...
+[2023-02-25 19:23:30,119][00219] Num frames 4600...
+[2023-02-25 19:23:30,229][00219] Num frames 4700...
+[2023-02-25 19:23:30,338][00219] Num frames 4800...
+[2023-02-25 19:23:30,452][00219] Avg episode rewards: #0: 21.896, true rewards: #0: 9.696
+[2023-02-25 19:23:30,454][00219] Avg episode reward: 21.896, avg true_objective: 9.696
+[2023-02-25 19:23:30,516][00219] Num frames 4900...
+[2023-02-25 19:23:30,630][00219] Num frames 5000...
+[2023-02-25 19:23:30,740][00219] Num frames 5100...
+[2023-02-25 19:23:30,869][00219] Num frames 5200...
+[2023-02-25 19:23:30,986][00219] Num frames 5300...
+[2023-02-25 19:23:31,097][00219] Num frames 5400...
+[2023-02-25 19:23:31,254][00219] Avg episode rewards: #0: 20.147, true rewards: #0: 9.147
+[2023-02-25 19:23:31,256][00219] Avg episode reward: 20.147, avg true_objective: 9.147
+[2023-02-25 19:23:31,273][00219] Num frames 5500...
+[2023-02-25 19:23:31,384][00219] Num frames 5600...
+[2023-02-25 19:23:31,498][00219] Num frames 5700...
+[2023-02-25 19:23:31,608][00219] Num frames 5800...
+[2023-02-25 19:23:31,720][00219] Num frames 5900...
+[2023-02-25 19:23:31,841][00219] Num frames 6000...
+[2023-02-25 19:23:31,956][00219] Num frames 6100...
+[2023-02-25 19:23:32,076][00219] Num frames 6200...
+[2023-02-25 19:23:32,186][00219] Num frames 6300...
+[2023-02-25 19:23:32,329][00219] Num frames 6400...
+[2023-02-25 19:23:32,485][00219] Num frames 6500...
+[2023-02-25 19:23:32,641][00219] Num frames 6600...
+[2023-02-25 19:23:32,794][00219] Num frames 6700...
+[2023-02-25 19:23:32,957][00219] Num frames 6800...
+[2023-02-25 19:23:33,115][00219] Num frames 6900...
+[2023-02-25 19:23:33,274][00219] Num frames 7000...
+[2023-02-25 19:23:33,439][00219] Num frames 7100...
+[2023-02-25 19:23:33,604][00219] Num frames 7200...
+[2023-02-25 19:23:33,767][00219] Num frames 7300...
+[2023-02-25 19:23:33,928][00219] Num frames 7400...
+[2023-02-25 19:23:34,091][00219] Num frames 7500...
+[2023-02-25 19:23:34,293][00219] Avg episode rewards: #0: 25.554, true rewards: #0: 10.840
+[2023-02-25 19:23:34,295][00219] Avg episode reward: 25.554, avg true_objective: 10.840
+[2023-02-25 19:23:34,321][00219] Num frames 7600...
+[2023-02-25 19:23:34,488][00219] Num frames 7700...
+[2023-02-25 19:23:34,573][00219] Avg episode rewards: #0: 22.520, true rewards: #0: 9.645
+[2023-02-25 19:23:34,575][00219] Avg episode reward: 22.520, avg true_objective: 9.645
+[2023-02-25 19:23:34,711][00219] Num frames 7800...
+[2023-02-25 19:23:34,864][00219] Num frames 7900...
+[2023-02-25 19:23:35,029][00219] Num frames 8000...
+[2023-02-25 19:23:35,194][00219] Num frames 8100...
+[2023-02-25 19:23:35,362][00219] Num frames 8200...
+[2023-02-25 19:23:35,527][00219] Num frames 8300...
+[2023-02-25 19:23:35,690][00219] Num frames 8400...
+[2023-02-25 19:23:35,829][00219] Num frames 8500...
+[2023-02-25 19:23:35,947][00219] Num frames 8600...
+[2023-02-25 19:23:36,060][00219] Num frames 8700...
+[2023-02-25 19:23:36,125][00219] Avg episode rewards: #0: 22.786, true rewards: #0: 9.676
+[2023-02-25 19:23:36,126][00219] Avg episode reward: 22.786, avg true_objective: 9.676
+[2023-02-25 19:23:36,237][00219] Num frames 8800...
+[2023-02-25 19:23:36,345][00219] Num frames 8900...
+[2023-02-25 19:23:36,457][00219] Num frames 9000...
+[2023-02-25 19:23:36,569][00219] Num frames 9100...
+[2023-02-25 19:23:36,686][00219] Num frames 9200...
+[2023-02-25 19:23:36,794][00219] Num frames 9300...
+[2023-02-25 19:23:36,917][00219] Num frames 9400...
+[2023-02-25 19:23:37,049][00219] Avg episode rewards: #0: 22.456, true rewards: #0: 9.456
+[2023-02-25 19:23:37,051][00219] Avg episode reward: 22.456, avg true_objective: 9.456
+[2023-02-25 19:24:32,561][00219] Replay video saved to /content/train_dir/default_experiment/replay.mp4!