atari_wrapper.py 文件源码

def __init__(self, env, noop_max=30):
        """Sample initial states by taking random number of no-ops on reset.
        No-op is assumed to be action 0.
        """
        gym.Wrapper.__init__(self, env)
        self.noop_max = noop_max
        self.override_num_noops = None
        if isinstance(env.action_space, gym.spaces.MultiBinary):
            self.noop_action = np.zeros(self.env.action_space.n, dtype=np.int64)
        else:
            # used for atari environments
            self.noop_action = 0
            assert env.unwrapped.get_action_meanings()[0] == 'NOOP'