PPO LunarLander-v2 trained agent version 4

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 284.11 +/- 19.29
+      value: 281.37 +/- 14.17
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa7893211030238b150b80a10b1a0367940083138991e8127224efebe713e38
+oid sha256:e3713d2e662b0bec62039bf925d13425567cd131fffe8f9db8a55b3df580e2ef
 size 144001

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b90666cc1cd3b1cd5e6907ed2b9102653fd0e858ddd6ed2d5f56d2d313f270
-size 221171
+oid sha256:0bf50459f7704580e5a1bfb2a99346029f48399da5932792a5891398e7bab5f6
+size 211219

results.json

@@ -1 +1 @@
-{"mean_reward": 284.1110354634138, "std_reward": 19.294926274620643, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T22:59:47.492172"}
+{"mean_reward": 281.36551337779434, "std_reward": 14.166544516438595, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T23:01:10.859817"}