Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -165.43 +/- 163.16
+      value: -151.21 +/- 88.39
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0002
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1732731798.45d7fe83a2d9.6974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa676d8945758d3de06eab1d042baacdfca2cb0f65338f912e0fd9313ea2f7a
+size 214749

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99c0eb6374547625d93179ea9efdd4b688ff49f7928d77111ddc1c81848201d
+oid sha256:e2608c32e3af11cb6a92dd4cf40cebd87d6a0d08801d4bacb52ae4edb8f3a237
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -165.4327028025198, "std_reward": 163.16202385339415, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:12:20.637696"}
+{"env_id": "LunarLander-v2", "mean_reward": -151.21312477880878, "std_reward": 88.39487193931222, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:24:44.858087"}