environments.py 文件源码

def act(self, action):
        try:
            assert not self.terminal()
        except AssertionError as e:
            e.args += ('Further action not permitted: terminal state ' +
                       ' reached. Episode is over.',)
            raise

        probs = self.T[action][self.state, :]
        pmf = stats.rv_discrete(name='pmf',
                                values=(self.states, probs))
        successor_state = pmf.rvs()
        self.state = successor_state

        r = self.rewards[successor_state]
        return r