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)
TODO: Add your code
import gym
from huggingface_sb3 import load_from_hub, package_to_hub, push_to_hub
from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.
from stable_baselines3 import PPO
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.env_util import make_vec_env
# Create the environment
env = make_vec_env('LunarLander-v2', n_envs=16)
# Define a PPO MlpPolicy architecture
model = PPO(
policy = 'MlpPolicy',
env = env,
n_steps = 1024,
batch_size = 64,
n_epochs = 4,
gamma = 0.999,
gae_lambda = 0.98,
ent_coef = 0.01,
verbose=1)
# Train the policy for 1,000,000 timesteps
model.learn(total_timesteps=int(1e6))
model_name = "lunar-landing-agent-sid"
model.save(model_name)
# Evaluate policy
# Create a new environment for evaluation
eval_env = gym.make("LunarLander-v2")
# Evaluate the model with 10 evaluation episodes and deterministic=True
mean_reward, std_reward = evaluate_policy(model, eval_env,10, True)
# Print the results
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
# Package to hub
from stable_baselines3.common.vec_env import DummyVecEnv
from stable_baselines3.common.env_util import make_vec_env
from huggingface_sb3 import package_to_hub
repo_id = "sidraina/ppo-LunarLander-v2"
env_id = "LunarLander-v2"
# Create the evaluation env
eval_env = DummyVecEnv([lambda: gym.make(env_id)])
model_architecture = "PPO"
commit_message = "First PPO LunarLander-v2 trained agent"
# method save, evaluate, generate a model card and record a replay video of your agent before pushing the repo to the hub
package_to_hub(model=model,
model_name=model_name,
model_architecture=model_architecture,
env_id=env_id,
eval_env=eval_env,
repo_id=repo_id,
commit_message=commit_message)
...