/RL_signals

All you need to know about Reinforcement Learning for Traffic Signal Control. https://traffic-signal-control.github.io/

Reinforcement Learning for Traffic Signal Control

The aim of this repository is to offering comprehensive dataset, simulator, relevant papers and survey to anyone who may wish to start investigation or evaluate a new algorithm.

Table of contents

Key paper list

Method Paper Published Notes Code Demo video Poster
MPLight Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control AAAI'2020 A combination of PressLight and FRAP - Demo -
CoLight CoLight: Learning Network-level Cooperation for Traffic Signal Control CIKM'19 Attention-based coordination Code N/A poster
PressLight PressLight: Learning Max Pressure Control to Coordinate Traffic Signals in Arterial Network KDD'19 Pressure-based coordination Code Demo poster
FRAP Learning Phase Competition for Traffic Signal Control CIKM'19 Our most powerful single intersectiton control model Code N/A poster
MetaLight MetaLight: Value-based Meta-reinforcement Learning for Traffic Signal Control AAAI'2020 Meta-RL for traffic signal control] Code - -
DemoLight Learning Traffic Signal Control from Demonstrations CIKM'19 Learn from expert demonstrations Code N/A poster
IntelliLight IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control KDD'18 First try on RL signal control. The base of all the methods N/A Demo poster
CityFlow CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario WWW'19 Demo Simulator Code Demo N/A

Open datasets

We provide different traffic datasets, each includes both road network (roadnet.json) and traffic flow file (flow.json), whose formats are defined in Roadnet File Format and Flow File Format respectively.

*All methods are measured in Average Travel Time (in seconds) under CityFlow simulator.
# Dataset name Number of Intersections Time Span (Seconds) Description Referred result* Referred method
1 hangzhou_1x1_bc-tyc_18041607_1h 1 3600 These datasets are based on camera data in Hangzhou. Due to the lack of records about turning vehicles, the turning ratios of each dataset are fixed, with 10% as turning left, 60% as going straight, and 30% as turning right. The turning-right vehicles are discarded since they are not under the control of traffic lights. There are one left-turn lane and one straight lane in each direction in each roadnet. 221.03 SOTL
2 hangzhou_1x1_bc-tyc_18041608_1h 1 3600 334.72 SOTL
3 hangzhou_1x1_bc-tyc_18041610_1h 1 3600 213.20 SOTL
4 hangzhou_1x1_kn-hz_18041607_1h 1 3600 72.48 SOTL
5 hangzhou_1x1_kn-hz_18041608_1h 1 3600 64.10 SOTL
6 hangzhou_1x1_qc-yn_18041607_1h 1 3600 117.24 SOTL
7 hangzhou_1x1_qc-yn_18041608_1h 1 3600 131.99 SOTL
8 hangzhou_1x1_sb-sx_18041607_1h 1 3600 173.85 SOTL
9 hangzhou_1x1_sb-sx_18041608_1h 1 3600 290.00 SOTL
10 hangzhou_1x1_tms-xy_18041607_1h 1 3600 214.77 SOTL
11 hangzhou_1x1_tms-xy_18041608_1h 1 3600 325.32 SOTL
12 syn_1x1_uniform_200_1h 1 3600 These datasets are generated artificially. The vehicles enter the road network uniformly with a fixed entering ratio chosen from 200, 400 and 600 vehicles per hour. 61.44 SOTL
13 syn_1x1_uniform_400_1h 1 3600 133.40 SOTL
14 syn_1x1_uniform_600_1h 1 3600 189.11 SOTL
15 hangzhou_4x4_gudang_18010207_1h 16 3600 The road network contains 16 intersections in a 4x4 grid. Each intersection has four incoming approaches and four outgping approaches, and each approach has three lanes (left-turn, through and right-turn respectively). The traffic flow data is based on camera data in Hangzhou. Necessary simplification is done due to the low quality of the real-world data. • Traffic volume: the traffic volume is derived from camera data at Hangzhou. • Turning ratio: 10% (turning left), 60%(going straight) and 30% (turning right). This is synthesized from the statistics of taxi GPS data. 240.97 MaxPressure
16 syn_1x3_gaussian_500_1h 3 3600 The road network contains 16 intersections in a 4x4 grid. Each intersection has four incoming approaches and four outgping approaches, and each approach has three lanes (left-turn, through and right-turn respectively). • Traffic volume: All the vehicles enter and leave the network from the rim edges.For each entering edge, the number of the vehicles generated is sampled from a Gaussian distribution with mean as 500 vehicles/hour/lane. • Turning ratio: 10% (turning left), 60%(going straight) and 30% (turning right) 422.95 MaxPressure
17 syn_2x2_gaussian_500_1h 4 3600 477.71 MaxPressure
18 syn_3x3_gaussian_500_1h 9 3600 631.75 MaxPressure
19 syn_4x4_gaussian_500_1h 16 3600 689.68 MaxPressure
20 Manhattan 2510 3600

Survey

A Survey on traffic signal control

Team

  • Zhenhui Jessie Li (Associate professor, Penn State)
  • Hua Wei (PhD, Penn State University)
  • Guanjie Zheng (PhD, Penn State University)
  • Chacha Chen (PhD, Penn State University)
  • Nan Xu (PhD, University of Southern California)
  • Yuanhao Xiong (PhD, University of Los Angelos)
  • Kan Wu (PhD, Penn State University)
  • Xinshi Zang (Bachelor, Shanghai Jiao Tong University)
  • Huichu Zhang (PhD, Shanghai Jiao Tong University)
  • Jie Feng (PhD, Tsinghua University)