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: -212.57 +/- 112.95
+      value: 5.63 +/- 66.32
       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.1746711299.8815686de3e6.9675.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f0d8f06edd96814a230f1090132b06b55c01466afe1c2320dce610946789fa
+size 675380

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.57079825900223, "std_reward": 112.94778872365691, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-08T13:30:58.132568"}
+{"env_id": "LunarLander-v2", "mean_reward": 5.627939059477958, "std_reward": 66.32257216162205, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-08T13:48:56.327876"}