Push PPO agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -202.89 +/- 95.45
+      value: -110.03 +/- 79.03
       name: mean_reward
       verified: false
 ---
@@ -36,7 +36,7 @@ This is a trained model of a PPO agent playing LunarLander-v2.
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 8
 'num_steps': 2048

logs/events.out.tfevents.1754231421.43abc99fdb1e.35327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e48722e6287c5373929d6fc744b2f5d46cedd13218a2295069ef050b803855
+size 2283

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760c804c0e0cc3877a52c5c761c69dc3436e7c86b2a3c808057312454d7077e0
+oid sha256:d836cc449c075a359d7a0a06cdc6a7369eb119f4efe5098ae148b01ce1a71da5
 size 147602

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -202.89347043112167, "std_reward": 95.45282050549824, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T14:29:38.293371"}
+{"env_id": "LunarLander-v2", "mean_reward": -110.02536891474179, "std_reward": 79.02843538923116, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T14:31:08.729530"}