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-v3
     metrics:
     - type: mean_reward
-      value: -123.25 +/- 48.96
+      value: 48.14 +/- 95.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v3'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1770180428.146a01270f08.11081.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d228ba0182feb3228beef0b7dfaaf75723f2064f22fcbca44d0ed6fb5d4cf0d
+size 503096

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473c7b6cc98f6c1ff0c3d95aa4d81ea1797a3cf75e89218688eb5af13a521a3e
+oid sha256:16bf5b8b731ae5f5dc73aacccef26b3c31996145f64d6b8b2262231074282e7c
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -123.25271327548035, "std_reward": 48.95733366853711, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-04T04:45:54.245213"}
+{"env_id": "LunarLander-v3", "mean_reward": 48.138140264311474, "std_reward": 95.24347115115654, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-04T04:53:01.096712"}