humanoid17

from stable_baselines3 import PPO
import gymnasium as gym

# Load the trained model
model = PPO.load("bipedal_walker_ppo_model")

# Create environment
env = gym.make('BipedalWalker-v3', render_mode='human')

# Watch it walk!
obs, _ = env.reset()
for _ in range(2000):
    action, _ = model.predict(obs, deterministic=True)
    obs, reward, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        obs, _ = env.reset()

env.close()