rl_example.py 文件源码

def __init__(self, row, column):
        self.rewards = np.full((row, column), -0.2)
        self.states = np.ones((row, column), dtype=np.int)
        self.states[1, 1] = -1

        self.index_list = [index for index, x in np.ndenumerate(self.states) if x > 0]
        self._init_next_state_table()

        self.rewards[0, column - 1] = 1
        self.rewards[0, 0] = 1
        self.rewards[1, column - 1] = -1

        self.terminal = [(0, column - 1), (0, 0)]