Inequity aversion reduces travel time in the traffic light control problem

02/23/2023

∙

The traffic light control problem is to improve the traffic flow by coordinating between the traffic lights. Recently, a successful deep reinforcement learning model, CoLight, was developed to capture the influences of neighboring intersections by a graph attention network. We propose IACoLight that boosts up to 11.4 Inequity Aversion (IA) model that reshapes each agent's reward by adding or subtracting advantageous or disadvantageous reward inequities compared to other agents. Unlike in the other applications of IA, where both advantageous and disadvantageous inequities are punished by considering negative coefficients, we allowed them to be also rewarded and explored a range of both positive and negative coefficients. Our experiments demonstrated that making CoLight agents averse to inequities improved the vehicles' average travel time and rewarding rather than punishing advantageous inequities enhanced the results.

READ FULL TEXT

Inequity aversion reduces travel time in the traffic light control problem

Optimizing Traffic Lights with Multi-agent Deep Reinforcement Learning and V2X communication

CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learning

EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Multi-Agent Broad Reinforcement Learning for Intelligent Traffic Light Control

Diagnosing Reinforcement Learning for Traffic Signal Control

Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks

Gamma-Reward: A Novel Multi-Agent Reinforcement Learning Method for Traffic Signal Control

Inequity aversion reduces travel time in the traffic light control problem

Related Research

Optimizing Traffic Lights with Multi-agent Deep Reinforcement Learning and V2X communication

CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learning

EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Multi-Agent Broad Reinforcement Learning for Intelligent Traffic Light Control

Diagnosing Reinforcement Learning for Traffic Signal Control

Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks

Gamma-Reward: A Novel Multi-Agent Reinforcement Learning Method for Traffic Signal Control