gridworld.py 文件源码

def __init__(self,
      dimensions=(3, 4),
      start_state=(0, 0),
      end_states=[(0, 3), (1, 3)],
      nonstates = [(1, 1)],
      state_rewards = {(0, 3): 1, (1, 3): -1},
      step_reward = -0.1,
      max_steps = 100):
    self.dimensions = dimensions
    self.states = set(np.ndindex(dimensions)).difference(set(nonstates))
    self.start_state = start_state
    self.end_states = end_states
    self.state_rewards = state_rewards
    self.step_reward = step_reward
    self.max_steps = max_steps
    assert self.is_state(self.start_state)
    assert all(self.is_state(state) for state in self.end_states)
    assert all(not self.is_state(state) for state in nonstates)
    self.start_episode()