Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -89.40 +/- 92.82
+      value: 179.78 +/- 85.54
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00025
+'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1716464983.98d39517c90d.24512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c752646aea5fe7b30874c3d04c33cc622bc7a0428dd913466c01ccdab6d0c2ab
+size 148697

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a168efbaa199a3e8a3b9a054d7d4f93f2a4b8e0ced4ca5f4285e1f18c3f9dc39
+oid sha256:2e3ea62c9bde8131537be8d1a8a4d2d1b72e05fb1cf758d920cb0cfd5ca1534b
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -89.39829122257106, "std_reward": 92.82373938189099, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:46:32.856504"}
+{"env_id": "LunarLander-v2", "mean_reward": 179.7790826374136, "std_reward": 85.5404023392251, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:52:01.647754"}