search

jkulhanek / robot-visual-navigation

Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning Official Implementation
MIT License
58 stars 11 forks source link

about image transform #22

Open GongYanfu opened 1 year ago

GongYanfu commented 1 year ago

image for the function observation: the pixel value of input image numpy array ranges from 0 to 255, and pixel value of output image ranges from -3.332 to 1.593, its not from -1.0 to 1.0, why? but there is the gym.space.Box(-1.0, 1.0)

GongYanfu commented 1 year ago

whats the intention of the function observation?

jkulhanek commented 1 year ago

The ranges of the gym.space.Box are not used anywhere in the code, so they can be arbitrary. The ranges were computed such that the images should have zero mean and a variance of 1.