Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.37 +/- 96.35
+      value: -139.55 +/- 47.05
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.001
+'learning_rate': 1e-06
 'num_envs': 16
 'num_steps': 512
 'anneal_lr': True

logs/events.out.tfevents.1685094072.2850cb3f29b2.20193.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673f423d0d16d435b3d31cc8a15debc2c278dce6187da2b22792065db28e32b1
+size 63638

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ffa03898b244e0e5c96f71882cdc3d8ae5c36348d50d442f8fb0bf75d7795f7
+oid sha256:68a564de40d8b19173a3c1ab59d004c5cde2e2f6f3a424c0eb2331fe867e9ed8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.37309354706989, "std_reward": 96.34637960793312, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:40:55.428676"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.55403828817452, "std_reward": 47.05304878690018, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:41:31.836426"}