Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -169.30 +/- 98.06
+      value: -109.89 +/- 63.45
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1681644439.6bee1a467f56.5322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e9d32f4a3531a8fe7102cf31dda6336d151c8318c9f3ebb3ac0572a159bf13
+size 214491

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:1679008ff97cb6c0add71cbe9fe3bd4d47a1bd6790325605239467d822ddabb0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -169.30208607884467, "std_reward": 98.05943666354497, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-16T11:26:00.307651"}
+{"env_id": "LunarLander-v2", "mean_reward": -109.89316362228521, "std_reward": 63.44945439205146, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-16T11:28:43.712319"}