Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 155.31 +/- 105.51
+      value: 107.60 +/- 82.60
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 100000
+'total_timesteps': 150000
 'torch_deterministic': True
 'cuda': True
 'track': True

logs/events.out.tfevents.1766087709.n-62-20-1.2699772.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9445fbc6838dfba488d2fce1da1eefa476bd4af318c4476b72e4124759e678a6
+size 4852455

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c370b4be6527be2ced838bc56542c0e02e03be52210eb9bb073803bec4bf5da1
+oid sha256:be82b199a2488e6d0f84f05ee8ead90f3b6b0a51b6999219f447fb3a4d55e50b
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 155.3136532945241, "std_reward": 105.51052560758883, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-17T23:35:12.848782"}
+{"env_id": "LunarLander-v2", "mean_reward": 107.60335285911106, "std_reward": 82.60173839158603, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-18T21:09:35.797300"}