gym环境调用step()时报错

Question

gym环境调用step方法报错too many values to unpack (expected 4)

用代码块功能插入代码，请勿粘贴截图

import gym
env=gym.make("ALE/Pong-v5")
env.reset()
env.step(env.action_space.sample())

运行结果及报错内容

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_32796/3015435202.py in <module>
      2 env=gym.make("ALE/Pong-v5")
      3 env.reset()
----> 4 env.step(env.action_space.sample())

d:\app\Anaconda\envs\pytorchEnv\lib\site-packages\gym\wrappers\order_enforcing.py in step(self, action)
     11     def step(self, action):
     12         assert self._has_reset, "Cannot call env.step() before calling reset()"
---> 13         observation, reward, done, info = self.env.step(action)
     14         return observation, reward, done, info
     15 

ValueError: too many values to unpack (expected 4)

这个问题应该如何解决？这就是单纯的调用环境而已，实在不知道怎么搞的。