skills/stable-baselines3/scripts/train_rl_agent.py

• train_agent · function · L24-L134 — def train_agent( env_id="CartPole-v1", algorithm=PPO, policy="MlpPolicy", n_envs=4, total_timesteps=100000, eval_freq=10000, save_freq=10000, log_dir="./logs/", save_path="./models/", )