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: -180.07 +/- 139.64
+      value: 27.91 +/- 99.38
       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.1748464055.33906ef95a39.6667.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6a8a5bb5e0a9c55b6ac34560d142a7f8e975602919027994a0b94f2d2eb13e
+size 640882

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
-size 43026
+oid sha256:486ee315a036fa5ddfe440dc807e7eec5f68617fdaadcf8bdfc5e4b7c268cf35
+size 139346

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.06667862195522, "std_reward": 139.6364580058691, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-28T20:24:04.235661"}
+{"env_id": "LunarLander-v2", "mean_reward": 27.91184337001141, "std_reward": 99.37693719209852, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-28T20:42:03.430466"}