README.md

---
tags:
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
- LunarLander-v2
model-index:
- name: PPO
  results:
  - task:
      type: reinforcement-learning
      name: LunarLander-v2
    dataset:
      name: LunarLander-v2
      type: LunarLander-v2
    metrics:
      - type: mean_reward
        value: 273 +/- 9.50  # <--- 请修改这里的数字：你的均值 +/- 你的标准差
        name: mean_reward
---

# PPO Agent for LunarLander-v3 (Optimized)

This is a pre-trained model for **LunarLander-v3** using Stable-Baselines3.

## Usage

```python
import gymnasium as gym
from stable_baselines3 import PPO
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.vec_env import VecNormalize

# Load the environment
env = make_vec_env("LunarLander-v3", n_envs=1)
env = VecNormalize.load("vec_normalize.pkl", env)
env.training = False
env.norm_reward = False

# Load the model
model = PPO.load("ppo_lunar_optimized", env=env)