gym_env.py 文件源码

def __init__(self, name, horizon, gamma):
        """
        Constructor.

        Args:
             name (str): gym id of the environment;
             horizon (int): horizon of the MDP;
             horizon (int): the horizon;
             gamma (float): the discount factor.

        """
        self.__name__ = name

        # MPD creation
        self.env = gym.make(self.__name__)

        self.env._max_episode_steps = np.inf  # Hack to ignore gym time limit.

        # MDP properties
        assert not isinstance(self.env.observation_space,
                              gym_spaces.MultiDiscrete)
        assert not isinstance(self.env.action_space, gym_spaces.MultiDiscrete)

        action_space = self._convert_gym_space(self.env.action_space)
        observation_space = self._convert_gym_space(self.env.observation_space)
        mdp_info = MDPInfo(observation_space, action_space, gamma, horizon)

        if isinstance(action_space, Discrete):
            self._convert_action = self._convert_action_function
        else:
            self._convert_action = self._no_convert

        if isinstance(observation_space,
                      Discrete) and len(observation_space.size) > 1:
                self._convert_state = self._convert_state_function
        else:
            self._convert_state = self._no_convert

        super(Gym, self).__init__(mdp_info)