Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -110.92 +/- 90.47
+      value: 35.55 +/- 46.79
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1751464377.7c6da54d0a13.14393.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75501b87ed91c229c0225afc2255cb156a28cf09e5b202388a3aca27ca68b54f
+size 675365

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c22fe87ba303c0fc46916ca93796158ba21cc55b7409a646835488f28dfcfd
+oid sha256:407537f42c3f2d84a7984a8b77eaefac4b67fc8c8f348e2bd567e73394507e87
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -110.91612066837881, "std_reward": 90.46587312143438, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T13:52:04.350515"}
+{"env_id": "LunarLander-v2", "mean_reward": 35.54728613848199, "std_reward": 46.7925751000324, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:07:22.435266"}