Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -21.37 +/- 54.66
+      value: 4.46 +/- 83.11
       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': 0.0003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1760011583.cfc0f405fae3.369.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083735db9ff8b639db85f78b2f8b2e98814a564f09e9568e5e6c65fd4daa8495
+size 167269

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04e4c9f03b21fa203086d9c237d215a321fac24fb68d8c96a69c53d2d4d809e
+oid sha256:887829e80c434d32e5cf6a650c0408667018fb8a9d4e879ee5de31cde58ffc49
 size 276266

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -21.370166619777667, "std_reward": 54.662461255164786, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-09T12:02:51.259938"}
+{"env_id": "LunarLander-v2", "mean_reward": 4.46158430330894, "std_reward": 83.1082308682976, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-09T12:08:41.753730"}