cliff_walking.py 文件源码

def _calculate_transition_prob(self, current, delta):
        new_position = np.array(current) + np.array(delta)
        new_position = self._limit_coordinates(new_position).astype(int)
        new_state = np.ravel_multi_index(tuple(new_position), self.shape)

        # Newer version of rewards/costs from G-learning paper
        # reward = -100.0 if self._cliff[tuple(new_position)] else -1.0
        reward = -1.0
        if self._cliff[tuple(new_position)]:
            reward = -100.0
        elif tuple(new_position) == (3,11):
            reward = 0.0

        is_done = self._cliff[tuple(new_position)] or (tuple(new_position) == (3,11))
        return [(1.0, new_state, reward, is_done)]