This repo provides OpenAI Gym compatible environments for traffic light control scenario and a bunch of baseline methods.
Environments include single intersetion (single-agent) and multi intersections (multi-agents) with different road network and traffic flow settings.
Baselines include traditional TLC algorithms and reinforcement learning based methods.
- Adds flow and roadmap files from Colight's repo
- Random agent for lower bound performance
- (WIP) Better and unified logging without conflicting files. (copying what was done with run_dqn.py)
- (WIP) Insta plotting
- CityFlow
- Tensorflow 1.1x
- OpenAI gym
- Numpy
Just run any of the run_* scripts
python run_dqn.py