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: -66.53 +/- 47.04
+      value: 31.92 +/- 95.07
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1742866076.j-sim.13419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07bf72b19e7daf68714b70106b6442a7bca0f6c94ddc1277030a75bcffd01cb
+size 672885

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e73812fd69918db2ec17c5bd383ce032d3d95d6683abca6bcc294a5f0ef5bbe7
+oid sha256:ae4dcc89e45d18feb0ce04c946d21bc04f0c16e73d5fd29f5ee2e5e7503525ac
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -66.53339251779025, "std_reward": 47.03581458100501, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-24T18:27:10.869062"}
+{"env_id": "LunarLander-v2", "mean_reward": 31.922393544648305, "std_reward": 95.06851441955355, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-24T18:36:03.498908"}