PPO LunarLander-v2 trained agent version 3

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 281.85 +/- 13.71
+      value: 282.15 +/- 19.33
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8cbf164852d78e99ef4d0b57235c8c3fc40fd08aa2daef3adb828bda652672
+oid sha256:045a932f7684a2524fb091b3241888b381ef09f0d0cba9657eb344dad59e8e02
 size 145169

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab722a7c70e3e9dabf3ce45d3d3e71cde2b7f74b77eaa2843072358860f9394
-size 208705
+oid sha256:cade9efa473bdce9bf494de90a518d4fdea02a302f677706977079791fe379c7
+size 192751

results.json

@@ -1 +1 @@
-{"mean_reward": 281.8537377495867, "std_reward": 13.71197126693284, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T21:53:24.871642"}
+{"mean_reward": 282.1502224003632, "std_reward": 19.327779453795294, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T21:55:43.949433"}