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

Reward #26

Open kgayush opened 3 years ago

kgayush commented 3 years ago

Reward is sum of cumulative wait time, right? How it is going negative in the graph(after running testing_main.py)? plot_reward

GangSuUGA commented 3 years ago

I think the reward is defined as the difference of cumulative wait time between the action intervals. So positive or negative rewards will be recevied.