Skip to yearly menu bar Skip to main content


Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets

Yifei Min · Tianhao Wang · Ruitu Xu · Zhaoran Wang · Michael Jordan · Zhuoran Yang

Hall J (level 1) #1036

Keywords: [ sequential matching ] [ matching ] [ dynamic matching ] [ optimal matching ]


We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market.At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner controls the transition of the contexts to maximize the cumulative social welfare, while the agents aim to find a myopic stable matching at each step. Such a setting captures a range of applications including ridesharing platforms. We formalize the problem by proposing a reinforcement learning framework that integrates optimistic value iteration with maximum weight matching. The proposed algorithm addresses the coupled challenges of sequential exploration, matching stability, and function approximation. We prove that the algorithm achieves sublinear regret.

Chat is not available.