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: -215.54 +/- 101.36
+      value: -61.20 +/- 15.01
       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.1759592554.homeserver01.1243987.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff315ec77a5f33e6744ab0ffe931bc96e7d89722670e3a623dd773652ea1554
+size 674629

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e820e598469ef3935922365726cef15cd910521c3eecdbfa058544ec207c42
+oid sha256:19ba8b1daad72de849cae97a75979d4f4e4e5432c220ff1915fb4e495cd39941
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -215.53739396376363, "std_reward": 101.35753384249351, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-04T23:16:04.446644"}
+{"env_id": "LunarLander-v2", "mean_reward": -61.19837655193369, "std_reward": 15.010882454457438, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-04T23:58:02.688092"}