Multiagent Reinforcement Learning for Traffic Light Simulation
- Follow the Flow documentation to setup Flow, SUMO and RLlib in the system. More tutorials and examples are available in the main repository of Flow.
- Activate virtual environment for flow and run train.py and simulate.py scripts in /Training as "python simulate.py EXP_CONFIG" or "python train.py EXP_CONFIG"
- Pre-trained models are present in /ray_results. Use "tensorboard --logdir ~/ray_results" to view the training statistics.
Key Papers and Datasets are available on https://traffic-signal-control.github.io/
Flow
Flow is a computational framework for deep RL and control experiments for traffic microsimulation.
See our website for more information on the application of Flow to several mixed-autonomy traffic scenarios. Other results and videos are available as well.
More information
Technical questions
If you have a bug, please report it. Otherwise, join the Flow Users group on Slack!
Getting involved
We welcome your contributions.
- Please report bugs and improvements by submitting GitHub issue.
- Submit your contributions using pull requests. Please use this template for your pull requests.
Citing Flow
If you use Flow for academic research, you are highly encouraged to cite our paper:
C. Wu, A. Kreidieh, K. Parvate, E. Vinitsky, A. Bayen, "Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control," CoRR, vol. abs/1710.05465, 2017. [Online]. Available: https://arxiv.org/abs/1710.05465
If you use the benchmarks, you are highly encouraged to cite our paper:
Vinitsky, E., Kreidieh, A., Le Flem, L., Kheterpal, N., Jang, K., Wu, F., ... & Bayen, A. M, Benchmarks for reinforcement learning in mixed-autonomy traffic. In Conference on Robot Learning (pp. 399-409). Available: http://proceedings.mlr.press/v87/vinitsky18a.html
Contributors
Flow is supported by the Mobile Sensing Lab at UC Berkeley and Amazon AWS Machine Learning research grants. The contributors are listed in Flow Team Page.