[英]How to correctly define this Observation Space for the custom Gym environment I am creating using Gym.Scpaces.Box?
I am trying to implement DDPG algorithm of the Paper .我正在尝试实现Paper的 DDPG 算法。
Here in the image below, gk[n] and rk[n] are KxM matrices of real values.在下图中,gk[n] 和 rk[n] 是 KxM 实数值矩阵。 Theta[n] and v[n] are arrays of size M.
Theta[n] 和 v[n] 是大小为 M 的 arrays。
I want to write correct code to specify state/observation space in my custom environment .我想编写正确的代码来在我的自定义环境中指定状态/观察空间。
Since the data type input to the neural.network needs to be unified, the state array can be expressed as由于需要统一输入到neural.network的数据类型,所以state数组可以表示为
observation_space = spaces.Box(low=0, high=1, shape=(K, M), dtype=np.float16......)
I am stuck.我卡住了。
If you use stable-baselines3, you may use a Dict
observation space filled with Box
es with meaningful limits for all your vectors and matrices (if limits are unknown, you may always use +inf/-inf
).如果你使用 stable-baselines3,你可以使用充满
Box
es 的Dict
观察空间,对你的所有向量和矩阵都有有意义的限制(如果限制未知,你可以总是使用+inf/-inf
)。 The code could be something like:代码可能是这样的:
from gym import Env
from gym.spaces import Box, Dict
class MySuperGymEnv(Env):
def __init__(self):
...
spaces = {
'theta': Box(low=0, high=1, shape=(99,), dtype=np.float32),
'g': Box(low=0, high=255, shape=(100,200), dtype=np.float32),
...
}
self.observation_space = Dict(spaces)
...
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.