Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 260.50 +/- 105.07
+      value: 287.70 +/- 123.56
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1716528445.0949425aa1ca.10761.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340bc3dd87a7625949fccb82f252f3ed283bc3ff43c5031e81cd7d03088c4eaf
+size 173399

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d38f85015109181b62f1488dbb4d4315b6e359bf697709ae2b8e98ab701cdc
+oid sha256:526afd9784da43303fc623c403d23ff9d3515b160a013158f9eca8a2d2b26583
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 260.5, "std_reward": 105.07354567159139, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T05:13:13.644353"}
+{"env_id": "CartPole-v1", "mean_reward": 287.7, "std_reward": 123.55569594316565, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T05:28:35.410858"}