primera versión del cursitoooooo

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: MlpPolicy
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 263.56 +/- 16.47
+      value: 246.93 +/- 42.48
       name: mean_reward
       verified: false
 ---
 
-# **MlpPolicy** Agent playing **LunarLander-v3**
-This is a trained model of a **MlpPolicy** agent playing **LunarLander-v3**
+# **PPO** Agent playing **LunarLander-v3**
+This is a trained model of a **PPO** agent playing **LunarLander-v3**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8b770a1202cf4583e196b8242ddb64cc9480446a96c06a8019c3e40fca985c
+oid sha256:d1108a6b3edee79d7166f6c02841e5db1d55e5316f52a16a78055834c428e1d8
 size 149937

results.json

@@ -1 +1 @@
-{"mean_reward": 263.56178609999995, "std_reward": 16.47146316402662, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-19T17:29:58.074011"}
+{"mean_reward": 246.9306539, "std_reward": 42.48284860645533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-19T17:34:07.098873"}