search

AndreaVidali / Deep-QLearning-Agent-for-Traffic-Signal-Control

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.
MIT License
405 stars 146 forks source link

Running Sumo-Gui #10

Closed grnm8 closed 4 years ago

grnm8 commented 4 years ago

Hello after the training is done. I wanted to create visualizations in SUMO of unoptimized traffic vs traffic that is optimized with neural networks. Visuals of before training vs after training. How do you suggest is the best way to do that? Thank you very much

AndreaVidali commented 4 years ago

I have just updated the code. Now it is possible to easily test the trained models and compare them using data generated by the test episode.