Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -142.71 +/- 96.24
+      value: -162.60 +/- 94.01
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 7e-05
+'learning_rate': 7e-06
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714949378.71d3fa3d3a00.19886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d287f96cf0c57f3e6c326f088d371c9d949727455576bd57ecfb0325c3afc5b
+size 229998

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad11988b9f6006f4fa06892ef72cd6c2ce9792c186170ce72c1c43fb5f0abcf
+oid sha256:1bca388f3156436ed0f0d6d6ffcc739ae501296b718e9e71f2082f27339280f0
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -142.71355558422906, "std_reward": 96.24427617216581, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:48:25.602822"}
+{"env_id": "LunarLander-v2", "mean_reward": -162.60487179732635, "std_reward": 94.01477441131019, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:51:01.579522"}