NotAnyMike / gym

An improvement of CarRacing-v0 from OpenAI Gym in order to make the environment complex enough for Hierarchical Reinforcement Learning
https://notanymike.github.io/
Other
70 stars 24 forks source link

on reset take N steps before returning, where N is the number of frames stack together #13

Closed NotAnyMike closed 5 years ago

NotAnyMike commented 5 years ago

Looks like the problem comes from the original environment. Things to do:

NotAnyMike commented 5 years ago

The solution was to allow

win.switch_to()
win.dispatch_events()