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: -168.12 +/- 79.47
+      value: 35.48 +/- 126.92
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 "wandb_entity": null
 "capture_video": false
 "env_id": "LunarLander-v2"
-"total_timesteps": 100000
+"total_timesteps": 1000000
 "learning_rate": 0.00025
 "num_envs": 4
 "num_steps": 128

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95dd02f0c06aaae1a3bb42545c1b51f2c83d17314bff678bd947aac34dad7f67
+oid sha256:f1175e77766c1edf3ba1aab7b48be0daf8516b5352d7f6f0985b94eb3a80feb4
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.1213346241725, "std_reward": 79.46986678282613, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-20T22:00:29.210915"}
+{"env_id": "LunarLander-v2", "mean_reward": 35.48205573046291, "std_reward": 126.91647740761145, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-20T22:34:48.961978"}