Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
  type: LunarLander-v2
  metrics:
  - type: mean_reward
- value: -200.37 +/- 73.91
+ value: -198.69 +/- 113.85
  name: mean_reward
  verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 2e-05
+'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1718026039.887b5cfc0142.15029.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34988f9a54aec91526592d0eec9aaf19bd8d9e756aaccf144613a51e662b02a2
+size 68676

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c2b4f6bbec26d6d381fb204a07994e8da94729d0e7c86b50317168857c0ee5
+oid sha256:9b5de41876adc4a31650a20abeb666e0b0311f0326f086df97ae82e91debb6a1
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -200.36639274859556, "std_reward": 73.91482615132544, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:26:17.286255"}
+{"env_id": "LunarLander-v2", "mean_reward": -198.69498259889008, "std_reward": 113.85473445032005, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:27:59.953429"}