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: -120.90 +/- 38.82
+      value: 10.75 +/- 122.75
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1764944571.1box.806026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cac67d952a7bf0526c40887527156f333bfd79b457cd91bb0fcee864a6d3323
+size 664102

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3b0d49b866cab146174104cccbe398ac31a156a10ffd0fff35f157f57dd3b9
+oid sha256:0f19e67ef1e54b30d33431701994ab9c64ff58acef6b32f9a6002f741a6e31c6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -120.90364976206938, "std_reward": 38.81607147909638, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-05T14:20:56.668941"}
+{"env_id": "LunarLander-v2", "mean_reward": 10.75021467649027, "std_reward": 122.74759155532217, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-05T14:27:30.173811"}