Paper List - Traffic Signal Control
This is a list of papers about traffic signal control in reinforcement learning, especially for some special traffic situation (including some traffic flow control papers).
T-junction & LR-intersection
- Traffic-signal control reinforcement learning approach for continuous-time Markov games: used a three-way intersection as an example, RL based
- Traffic design and signal timing of staggered intersections based on a sorting strategy: an LR-type staggered intersection of Shenhua Road and Zijinghua Road in the city of Hangzhou, China, not RL based
- Constrained Dynamic Control of Traffic Junctions: provide a competing real-time adaptive control strategy which through the use of dynamic programming, an T-junction example
- An automated signalized junction controller that learns strategies by temporal difference reinforcement learning: examples of T junction and LR intersection, RL based
- Parallel Reinforcement Learning for Traffic Signal Control, Parallel Reinforcement Learning with State Action Space Partitioning: T junction example, RL based
- Urban Traffic Control Using Distributed Multi-agent Deep Reinforcement Learning: RL based approach for multi agent traffic control with multi-type intersection
Highways
- Decentralised reinforcement learning for ramp metering and variable speed limits on highways: RL based traffic flow control on highways
- Multi-Agent Inverse Reinforcement Learning: RL based, simulation a traffic signal domain with 4 intersection near highway
- Traffic flow optimization: A reinforcement learning approach: traffic flow optimization on highway example, RL based
- A case for the adoption of decentralised reinforcement learning for the control of traffic flow on South African highways: control of traffic flow on highways, RL based
Bottleneck
- Adaptive Traffic Signal Control of Bottleneck Subzone based on Grey Qualitative Reinforcement Learning Algorithm: simulate a bottleneck subzone in Lianyungang using VISSIM, RL based
- A continuous-flow-intersection-lite design and traffic control for oversaturated bottleneck intersections: not RL based
- Lagrangian Control through Deep-RL: Applications to Bottleneck Decongestion:decongest bottleneck, RL based
- Differential Variable Speed Limits Control for Freeway Recurrent Bottlenecks via Deep Reinforcement learning: speed limit control for bottleneck, RL based
Others
- A Fast Method to Prevent Traffic Blockage by Signal Control Based on Reinforcement Learning: not focus on specific traffic environment, but using WNN for predicting traffic flow
- Multiagent Reinforcement Learning Algorithm for Distributed Dynamic Pricing of Managed Lanes: policy design for managed lanes
More to be added …