My first RL model using ppo on LunarLander-v2 environment

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 198.73 +/- 82.82
+      value: 192.58 +/- 81.25
       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:eae2c60b129a7c65f0cd15fd226381c21b1d6ea53b9e2918e95d4eb9d5a81bf9
+oid sha256:befcebbb14bcf331eab5d3b174341bc61a64f247dedaed49f9f198cb2c8d9d5d
 size 146495

results.json

@@ -1 +1 @@
-{"mean_reward": 198.73271331787177, "std_reward": 82.815113292267, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-09T17:19:05.428581"}
+{"mean_reward": 192.57630285017677, "std_reward": 81.2466621933505, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-09T17:23:31.702709"}