Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 287.70 +/- 123.56
+      value: 466.20 +/- 48.53
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 100000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1716528778.0949425aa1ca.10761.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c50134b29683484a88deb10572edf9c0a5ef877b9bc8d98b4d130d74949f599
+size 311316

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526afd9784da43303fc623c403d23ff9d3515b160a013158f9eca8a2d2b26583
+oid sha256:bde6f79b05b90ffc0f9a0e6409495fda1f5bbdc4cc51384d20af7bba3c3eef6d
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 287.7, "std_reward": 123.55569594316565, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T05:28:35.410858"}
+{"env_id": "CartPole-v1", "mean_reward": 466.2, "std_reward": 48.52793010215869, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T05:35:21.756148"}