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: -158.95 +/- 90.09
+      value: 12.96 +/- 77.95
       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.1741618100.e54037d5bda3.10871.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66028640df315c79af890c9ca16d5aa57eb2300d000ead60f469061df111897c
+size 673384

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+oid sha256:19bef862c6dfd08e434cb9e61b84a8162e39f50a283e75ede03a4820909da123
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -158.95442328475426, "std_reward": 90.08541669634768, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-10T14:46:47.904272"}
+{"env_id": "LunarLander-v2", "mean_reward": 12.96478246747347, "std_reward": 77.95195164457807, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-10T15:02:20.087747"}