PPO LunarLander-v2 trained agent version 4

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 279.07 +/- 16.60
+      value: 282.19 +/- 21.40
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49cf4683175c1b24b64dcfdecadc35694919a14b201f20b6579b376c52cc77e4
+oid sha256:53e20f412ad896e7dd2e2eb23dd760b691f820dfd8aaf61991fc7996feec882e
 size 144001

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3031a3c903009895ef6c08a594437e0a3f8c47bd4e85afbe0c88e9a46fb23fc5
-size 207260
+oid sha256:08acbe2ddaf761816676c9d1a0a81c6ef8f55473a90b5f09103c04fb420e15ab
+size 225913

results.json

@@ -1 +1 @@
-{"mean_reward": 279.07014247237356, "std_reward": 16.603090129205967, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T23:03:19.756335"}
+{"mean_reward": 282.18747174906264, "std_reward": 21.400760713673066, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T23:04:05.884235"}