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: -116.26 +/- 111.58
+      value: -54.72 +/- 23.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1750600132.1969e45f08d4.20582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200e5fbe3d9d3a546a5aded5188866c072206dae10aa984f506ed7dde5696f08
+size 479374

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bd5319b095542339353e0dd2b8a4aa060b7faabc96422593ebe514716dc311
+oid sha256:885b1281355fe09a8a1c78ebc97b7ed77b777a465eba276887fcbef1b1aabf9a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -116.25754947736183, "std_reward": 111.57605570641716, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-22T13:47:05.026996"}
+{"env_id": "LunarLander-v2", "mean_reward": -54.71918052632541, "std_reward": 23.240395287869443, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-22T14:00:55.841952"}