first rl model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 258.35 +/- 21.08
+      value: 261.11 +/- 11.32
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d10453c2adfe69767a3337378c9916a39295299102b210ff42b5a2d0720edad
+oid sha256:7c06429799b3ec9fa0eef81558ebe07a3c651ecefb1be21c67d48c91d5ff5cfe
 size 146702

results.json

@@ -1 +1 @@
-{"mean_reward": 258.3505457, "std_reward": 21.079188950165932, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T06:11:26.294554"}
+{"mean_reward": 261.11246910000006, "std_reward": 11.31877032161557, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T06:16:21.090741"}