PPO LunarLander-v2 trained agent version 4

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 277.43 +/- 17.95
+      value: 279.07 +/- 16.60
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78429590a29dd6146c008cef7d2d507f3a76473e3a83460dbbffb69041583a6c
+oid sha256:49cf4683175c1b24b64dcfdecadc35694919a14b201f20b6579b376c52cc77e4
 size 144001

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c56408407f521bf42f009c0f16939f5efd4115d731ff860a14265986ad3f51
-size 224826
+oid sha256:3031a3c903009895ef6c08a594437e0a3f8c47bd4e85afbe0c88e9a46fb23fc5
+size 207260

results.json

@@ -1 +1 @@
-{"mean_reward": 277.43009518302097, "std_reward": 17.953816327782892, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T23:01:49.491488"}
+{"mean_reward": 279.07014247237356, "std_reward": 16.603090129205967, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T23:03:19.756335"}