Upload README.md with huggingface_hub

README.md

@@ -1,37 +1,26 @@
 ---
+license: mit
 library_name: stable-baselines3
 tags:
-- LunarLander-v3
 - deep-reinforcement-learning
-- reinforcement-learning
-- stable-baselines3
-model-index:
-- name: PPO
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: LunarLander-v3
-      type: LunarLander-v3
-    metrics:
-    - type: mean_reward
-      value: 275.37 +/- 23.18
-      name: mean_reward
-      verified: false
+- gymnasium
+- lunar-lander
+- ppo
+- sb3
 ---
 
-# **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).
+# PPO LunarLander-v3
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+This repository contains a Stable-Baselines3 PPO agent trained to solve the Gymnasium LunarLander environment.
 
+## Training setup
+- Algorithm: PPO
+- Environment: LunarLander-v3
+- Policy: MlpPolicy
+- Training timesteps: 1,000,000
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+## Evaluation
+The agent was evaluated on the LunarLander environment with deterministic rollout settings.
 
-...
-```
+## Notes
+This model is intended for experimentation and educational purposes.