我对CartPole-v0
内省的观察空间感到惊讶。
据the official doc说,这是我应该得到的:
然而,这就是我得到的:
print(env.observation_space.low)
print(env.observation_space.high)
#[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]
#[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]
我正在使用latest version of gym
:
!pip list|grep gym
gym 0.12.1
知道发生了什么事吗?
正如代码中所记录的那样,您似乎正在获得预期的行为,这有点令人困惑。一方面,cart position
的观察空间为[-4.8,4.8],但实际上,当推车达到极限[-2.4,2.4]时,情节应该完成。与pole angle
情况类似。
class CartPoleEnv(gym.Env):
"""
Description:
A pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The pendulum starts upright, and the goal is to prevent it from falling over by increasing and reducing the cart's velocity.
Source:
This environment corresponds to the version of the cart-pole problem described by Barto, Sutton, and Anderson
Observation:
Type: Box(4)
Num Observation Min Max
0 Cart Position -4.8 4.8
1 Cart Velocity -Inf Inf
2 Pole Angle -24 deg 24 deg
3 Pole Velocity At Tip -Inf Inf
Actions:
Type: Discrete(2)
Num Action
0 Push cart to the left
1 Push cart to the right
Note: The amount the velocity that is reduced or increased is not fixed; it depends on the angle the pole is pointing. This is because the center of gravity of the pole increases the amount of energy needed to move the cart underneath it
Reward:
Reward is 1 for every step taken, including the termination step
Starting State:
All observations are assigned a uniform random value in [-0.05..0.05]
Episode Termination:
Pole Angle is more than 12 degrees
Cart Position is more than 2.4 (center of the cart reaches the edge of the display)
Episode length is greater than 200
Solved Requirements
Considered solved when the average reward is greater than or equal to 195.0 over 100 consecutive trials.
"""
在this link中,您可以阅读相关的Github问题。
*请注意,24度相当于4.1887903e-01弧度。
看起来像过时的文档,已经创建了一个问题:https://github.com/openai/gym/issues/368