Explore-then-Commit Algorithms for Decentralized Two-Sided Matching Markets

Tejas Pagare, Avishek Ghosh

Abstract: Online learning in a decentralized two-sided matching markets, where the demand-side (players) compete to match with the supply-side (arms), has received substantial interest because it abstracts out the complex interactions in matching platforms (e.g. UpWork, TaskRabbit). However, past works [1]–[5] assume that the each arm knows their preference ranking over the players (one-sided learning), and each player aim to learn the preference over arms through successive interactions. Moreover, several (impractical) assumptions on the problem are usually made for theoretical tractability such as broadcast player-arm match ( [1], [2], [5]) or serial dictatorship ( [3], [4], [6]). In this paper, we study a decentralized two-sided matching market, where we do not assume that the preference ranking over players are known to the arms apriori. Furthermore, we do not have any structural assumptions on the problem. We propose a multi-phase explore-then-commit type algorithm namely epoch-based CA-ETC (collision avoidance explore then commit) (CA-ETC in short) for this problem that does not require any communication across agents (players and arms) and hence decentralized. We show that for the initial epoch length of To and subsequent epoch-lengths of (for the l-th epoch with E (0,1) as an input parameter to the algorithm), CA-ETC yields a player optimal expected regret of ( ( for the i-th player, where $T$ is the learning horizon, $K$ is the number of arms and is an appropriately defined problem gap. Furthermore, we propose a blackboard communication based baseline achieving logarithmic regret in $T$.11Appendix at https://bit.ly/ISIT_matchingmarkets

External IDs:dblp:conf/isit/PagareG24