Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -212.96 +/- 110.81
+      value: -106.08 +/- 77.00
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 10000
-'learning_rate': 0.025
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677780408.6c4e5c51f044.15873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a4f36ed5f26a45493578d5e96bc88f4cfb543fc03b94ead75240e20bfe60ab
+size 20060

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290fc01ffdbcd7529ceddc2e5b96d28fbe9735ba5bb98f72d4e6f9fac78d71b1
+oid sha256:de5a6e339b4256c1f6f6b16baf2a1baa772084cddb7fadb98928957229b29b58
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.96045972546025, "std_reward": 110.80783724468003, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:06:12.242437"}
+{"env_id": "LunarLander-v2", "mean_reward": -106.07702309290815, "std_reward": 77.00171347872302, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:07:05.359811"}