first rl model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 261.11 +/- 11.32
+      value: 227.53 +/- 73.94
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c06429799b3ec9fa0eef81558ebe07a3c651ecefb1be21c67d48c91d5ff5cfe
+oid sha256:1d0bda5f491763f39338ddc9e5f03a1b8b46fc1ba3b895e3233559aee41040ee
 size 146702

results.json

@@ -1 +1 @@
-{"mean_reward": 261.11246910000006, "std_reward": 11.31877032161557, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T06:16:21.090741"}
+{"mean_reward": 227.5328396, "std_reward": 73.94469762646762, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-18T06:18:11.807087"}