table_base.py 文件源码

def __init__(self, env_name, num_episodes, alpha, gamma, epsilon, policy, **kwargs):
        """
        base class for RL using lookup table
        :param env_name: name of environment, currently environments whose observation space and action space are
        both Discrete are supported. see https://github.com/openai/gym/wiki/Table-of-environments
        :param num_episodes: number of episode for training
        :param alpha:
        :param gamma:
        :param epsilon:
        :param kwargs: other arguments.
        """
        super(TableBase, self).__init__(env_name, num_episodes, alpha, gamma, policy, epsilon=epsilon, **kwargs)

        if not isinstance(self.env.action_space, gym.spaces.Discrete) or \
                not isinstance(self.env.observation_space, gym.spaces.Discrete):
            raise NotImplementedError("action_space and observation_space should be Discrete")

        self.obs_size = self.env.observation_space.n
        self.action_size = self.env.action_space.n
        self.q_table = torch.zeros(self.obs_size, self.action_size)