PPO Model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 285.89 +/- 19.69
+      value: 272.06 +/- 21.36
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04396a74b1825c660b00b390509dde456d6c57266403dc2d38871bc90884a48
+oid sha256:b5e6bf8e676b8048e34c94354939f01c545c7ad231607d0115474deb35b283d7
 size 146069

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93645b07beacccb9661b4ed4f8a8721c3d702eac63b25577a3bf9eb953131a46
-size 191802
+oid sha256:b9314e95ac430dea11b5bc1f8fdb71559c9e357f2491271e1148fdf2a6a18c9a
+size 199054

results.json

@@ -1 +1 @@
-{"mean_reward": 285.89101464316343, "std_reward": 19.69123534154847, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T10:39:37.564207"}
+{"mean_reward": 272.06433075821144, "std_reward": 21.35560781750557, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T10:42:06.053298"}