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: -181.99 +/- 113.50
+      value: -29.99 +/- 89.46
       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.1754729817.7a41826ba486.32802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0798bdfa1451b56cf78ef74ff6d67bf48b481b9468094f427c41e0ce792e4e4e
+size 673753

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c13b819527e4b4806786c6b0fbd16ffe5efb389234fffdd9b8e5682d69f947f
+oid sha256:5d33fa5df8b52bccdf127def3f711c4e6d10cbd499aaf7ccaf49b57fc730aee6
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -181.9871456172073, "std_reward": 113.49870745842959, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-09T08:49:23.579068"}
+{"env_id": "LunarLander-v2", "mean_reward": -29.985515101492638, "std_reward": 89.4553870255669, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-09T09:09:52.182076"}