rl_utils.py 文件源码

def run_test_episode(env, policy, episode_len=np.inf, render=False):
    """
    Run an episode and return the reward
    """
    episode_itr = 0
    total_reward = 0.0
    done = False
    obs = env.reset()
    while not done and episode_itr < episode_len:
        if render:
            env.render()

        obs = apply_prediction_preprocessors(policy, obs)
        action = policy.predict(obs)
        action = apply_prediction_postprocessors(policy, action)

        obs, reward, done, _ = env.step(action)

        total_reward += reward
        episode_itr += 1

    return total_reward