PPO LunarLander-v2 re-trained agent with video fixed due to bugged HF package

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 290.23 +/- 20.94
+      value: 278.94 +/- 18.22
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e906dc1151ac2c66009851682d61a1217a845d4dc16b0a3cc48c18688e1ecb95
+oid sha256:4060585e3a9a1f2bc4c6bd191623a84265702d4e1d488aed4efd6c8d8a01e5d3
 size 148859

results.json

@@ -1 +1 @@
-{"mean_reward": 290.2311788, "std_reward": 20.943020903708824, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-22T04:45:32.949590"}
+{"mean_reward": 278.94102499999997, "std_reward": 18.222164961838534, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-22T04:46:29.766915"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9ea789cfb16c10f2fe8218b8bcb64553aeaf041d6b9ee4ee4cee8f1602817c
-size 1863
+oid sha256:bb5f4db33de9d87cd303d1a1c1e5671ab372fb99e88cfa42b53c93bbcdeb237a
+size 1889