search

araffin / learning-to-drive-in-5-minutes

Implementation of reinforcement learning approach to make a car learn to drive smoothly in minutes
https://towardsdatascience.com/learning-to-drive-smoothly-in-minutes-450a7cdb35f4
MIT License
284 stars 88 forks source link

clip_steering_diff() may return value out of action space #14

Closed wangyubin112 closed 4 years ago

wangyubin112 commented 4 years ago

Hi, While trying to make drive smoothly, clip_steering_diff() may return value out of action space. Does the simulator robust to the action value which is out of action space?

wangyubin112 commented 4 years ago

Sorry not an issue, I found that the action values are limited in other place.