Upload PPO LunarLander-v3 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 286.52 +/- 19.23
+      value: 289.28 +/- 17.67
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f701fef3dafdcb019f970ab76ada395beb04e87bed8585feff7e2cfdb45c077
+oid sha256:4d8560a51a672763f034d542ff800550d6d5ac8a55fde00d589f303dc99094cf
 size 143990

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ba54bda3727cf519febeb96fe0b17135c768f615cac6c014216fbea72b11a5
-size 199733
+oid sha256:612a75695a29545fed7ec766bd3770e6e1778d72b27d57413a744b9278034888
+size 147103

results.json

@@ -1 +1 @@
-{"mean_reward": 286.5166884018884, "std_reward": 19.22544595567936, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T09:46:28.872728"}
+{"mean_reward": 289.2845334288482, "std_reward": 17.671353299359147, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T09:48:41.647397"}