Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: -95.04 +/- 21.58
+      value: -97.25 +/- 36.07
       name: mean_reward
       verified: false
 ---
@@ -32,11 +32,11 @@ model-index:
 'N': 16
 'b': 8
 'lr': 0.02
-'normalizer': <__main__.Normalizer object at 0x00000282A0091120>
-'writer': <torch.utils.tensorboard.writer.SummaryWriter object at 0x00000282A0091750>
+'normalizer': <__main__.Normalizer object at 0x0000017A496510F0>
+'writer': <torch.utils.tensorboard.writer.SummaryWriter object at 0x0000017A49651720>
 'env_id': 'BipedalWalker-v3'
 'algorithm': 'ARS'
-'iterations': 30
+'iterations': 3000
 'episode_length': 5000
 'test_iterations': 100}
   ```

results.json

@@ -1 +1 @@
-{"env_id": "BipedalWalker-v3", "mean_reward": -95.03716054591457, "std_reward": 21.582224031703173, "n_evaluation_episodes": 100, "eval_datetime": "2024-01-07T10:58:06.497219"}
+{"env_id": "BipedalWalker-v3", "mean_reward": -97.25448595641689, "std_reward": 36.070083228644584, "n_evaluation_episodes": 100, "eval_datetime": "2024-01-07T13:12:41.004683"}