Upload Recurrent PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 263.59 +/- 38.24
+      value: 290.21 +/- 13.59
       name: mean_reward
       verified: false
 ---

recurrent-ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05c5bc5439e01ad73bd7fcf55775c2fb1b405c2868e355e4d4e142bd2d3b244
+oid sha256:f9eb7bbd11358f1eeb71071f763bd523c504c34a8eb79ee76471cb7803b1d5c7
 size 7163656

results.json

@@ -1 +1 @@
-{"mean_reward": 263.5891733498937, "std_reward": 38.238775053132265, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-06T12:41:20.832468"}
+{"mean_reward": 290.2083103893845, "std_reward": 13.586889647558298, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-06T12:44:49.032086"}