My second RL training attempt!

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -562.58 +/- 93.94
+      value: -527.34 +/- 152.21
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0147f6eca8d6997e5cd8a22893c06d253c5e9616f503a0dfc33d830bfcc21b63
+oid sha256:bd190ac3821a73c129245953571ef81a60a9905039328c6d7c45ae3fab9e686e
 size 107482

results.json

@@ -1 +1 @@
-{"mean_reward": -562.5759415, "std_reward": 93.93795511655733, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T17:52:49.680421"}
+{"mean_reward": -527.3373033, "std_reward": 152.21060679877596, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T18:01:57.834795"}