Stop Thinking, Just Do!

Sungsoo Kim's Blog

Controlling Traffic with Reinforcement Learning

tagsTags

26 April 2019


Article Source


Controlling Traffic with Reinforcement Learning

Abstract

Finally a good real-life use case for Reinforcement Learning (RL): traffic control! In this talk I will show you how we hooked up traffic simulation software to Python and how we built our own custom gym environment to run RL experiments with keras-rl for a simple 4-way intersection.

Reinforcement Learning based Traffic Signal Control Validated in Real-Time Real World Traffic

We implemented distributed Q-Learning based traffic signal control to optimize vehicles, pedestrians, and neighborhood traffic. Simulations of any cities with real-world map and traffic data show significant performance gains. For more details, please check: site


comments powered by Disqus