normalized_env.py 文件源码

def step(self, action):
        if isinstance(self._env.action_space, Box):
            # rescale the action
            lb = self._env.action_space.low
            ub = self._env.action_space.high
            scaled_action = lb + (action + 1.) * 0.5 * (ub - lb)
            scaled_action = np.clip(scaled_action, lb, ub)
        else:
            scaled_action = action

        wrapped_step = self._env.step(scaled_action)
        next_obs, reward, done, info = wrapped_step

        if self._normalize_obs:
            next_obs = self._apply_normalize_obs(next_obs)
        if self._normalize_reward:
            reward = self._apply_normalize_reward(reward)

        return next_obs, reward, done, info