PPO Agent playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library.
Usage (with Stable-baselines3)
import gymnasium as gym
from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub
from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.evaluation import evaluate_policy
repo_id = "Cesoft/ppo-LunarLander-v2"
filename = "ppo-LunarLander-v2.zip"
custom_objects = {
"learning_rate": 0.0,
"lr_schedule": lambda _: 0.0,
"clip_range": lambda _: 0.0,
}
checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
eval_env = Monitor(gym.make("LunarLander-v2", render_mode="human"))
mean_reward, std_reward = evaluate_policy(
model,
eval_env,
n_eval_episodes=EVAL_EPISODES,
deterministic=True,
render=True
)
eval_env.close()
print(f"mean_reward={mean_reward:.2f} +/- {std_reward} = {mean_reward - std_reward}")
...
- Downloads last month
- 17
Evaluation results
- mean_reward on LunarLander-v2self-reported251.04 +/- 23.05