primera versión del cursitoooooo

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 241.99 +/- 36.64
+      value: 238.94 +/- 53.97
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4074f52490fe0f3b0772098750562051a36a44b35f21cbccdee762a294dfafc3
+oid sha256:c83be17c03b4150c3c0dec4f31baf6e4f86518fd8ee8d48714b260cb17eb7bb0
 size 149937

results.json

@@ -1 +1 @@
-{"mean_reward": 241.98747270000004, "std_reward": 36.63712449673895, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-19T17:36:00.731429"}
+{"mean_reward": 238.9402295120889, "std_reward": 53.96990735191425, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-19T17:39:29.530608"}