Rate-Optimal Contextual Online Matching Bandit

Abstract

Two-sided online matching platforms have been employed in various markets. However, agents' preferences in the present market are usually implicit and unknown, and thus must be learned from data. With the growing availability of side information involved in the decision process, modern online matching methodology demands the capability to track preference dynamics for agents based on the contextual information. This motivates us to consider a novel Contextual Online Matching Bandit prOblem (COMBO), which allows dynamic preferences in matching decisions. Existing works focus on multi-armed bandit with static preference, but this is insufficient: the two-sided preference changes as long as one-side's contextual information updates, resulting in non-static matching. In this paper, we propose a Centralized Contextual -Explore Then Commit (CC-ETC) algorithm to adapt to the COMBO. CC-ETC solves online matching with dynamic preference. In theory, we show that CC-ETC achieves a sublinear regret upper bound O(log(T )) and is a rate-optimal algorithm by proving a matching lower bound. In the experiments, we demonstrate that CC-ETC is robust to variant preference schemes, dimensions of contexts, reward noise levels, and context variation levels.

Deep spectral Q‐learning with application to mobile health

“…Recently, there is a growing line of research in the statistics literature for policy learning and/or evaluation in infinite horizons. Some references include Chen et al (2022), Ertefaie and Strawderman (2018), Liao et al (2020), Liao et al (2021), Li et al (2022), Luckett et al (2020), Ramprasad et al (2022), Shi et al (2022, and Xu et al (2020). In the computer science literature, there is a huge literature on developing reinforcement learning (RL) algorithms in infinite horizons.…”