Trained 5M for Steps PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 288.32 +/- 17.79
+      value: 286.30 +/- 15.84
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-5M.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e388d55d5d3a1d2e9672791099bb073d8c6d27d713416c15f79433a3b7642f
+oid sha256:e255ff540f00ffa5ed8da92daad1c7fcab32c8f2c21690feda90a3b35dbcfb23
 size 146628

results.json

@@ -1 +1 @@
-{"mean_reward": 288.32379378910275, "std_reward": 17.786236243734482, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-15T14:45:42.296682"}
+{"mean_reward": 286.2979426406295, "std_reward": 15.835314907550982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-15T14:46:48.886332"}