觀察空間中的值太多：方框

Question

我在 OpenAI 中運行健身房教程，一開始就卡住了。 運行“MountainCar-v0”環境后，我希望 Obs 空間有 2 個值，但我得到 6 個。

`import gym
env = gym.make('MountainCar-v0')
obs_space = env.observation_space
action_space = env.action_space
print("The observation space: {}".format(obs_space))
print("The action space: {}".format(action_space))`

雖然我期待得到：

OUTPUT:
The observation space: Box(2,)
The action space: Discrete(3)

我正進入（狀態：

 The observation space: Box([-1.2 -0.07], [0.6 0.07], (2,), float32) The action space: Discrete(3)

這會在嘗試生成新的 obs 時導致下游錯誤：

obs = env.reset()
random_action = env.action_space.sample()
new_obs, reward, done, info = env.step(random_action)
print("The new observation is {}".format(new_obs))

我收到以下錯誤：

ValueError                                Traceback (most recent call last)
Input In [4], in <cell line: 11>()
      8 random_action = env.action_space.sample()
     10 # # Take the action and get the new observation space
---> 11 new_obs, reward, done, info = env.step(random_action)
     12 print("The new observation is {}".format(new_obs))

ValueError: too many values to unpack (expected 4)

Answer 1

我假設您使用的是最新版本的健身房，即0.26.2

根據此處提供的文檔，您的錯誤可以通過 -

import gym
env = gym.make('MountainCar-v0')
obs_space = env.observation_space
action_space = env.action_space
obs = env.reset()
random_action = env.action_space.sample()
observation, reward, terminated, truncated, info = env.step(random_action)