META: A City-Wide Taxi Repositioning Framework Based on Multi-Agent Reinforcement Learning

Abstract

The popularity of online ride-hailing platforms has made people travel smarter than ever before. But people still frequently encounter the dilemma of “ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">taxi drivers hunt passengers and passengers search for unoccupied taxis</i> ”. Many studies try to reposition idle taxis to alleviate such issues by using reinforcement learning based methods, as they are capable of capturing future demand/supply dynamics. However, they either coordinate all city-wide taxis in a centralized manner or treat all taxis in a region homogeneously, resulting in inefficient or inaccurate learning performance. In this paper, we propose a multi-agent reinforcement learning based framework named <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">META</b> ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>M</u></b> ak <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>E</u></b> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>T</u></b> axi <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>A</u></b> ct differently in each agent) to mitigate the disequilibrium of supply and demand via repositioning taxis at the city scale. We decompose it into two subproblems, i.e., taxi demand/supply determination and taxi dispatching strategy formulation. Two components are wisely built in <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">META</b> to address the gap collaboratively, in which each region is regarded as an agent and taxis inside the region can make two different actions. Extensive experiments demonstrate that <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">META</b> outperforms existing methods.