2025/03/11 by William Chang, Chang, William, Yuanhao Lu +1 · 1 citation
Decision Sciences · Social Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Machine Learning (cs.LG) #Misinformation and Its Impacts #Personal Information Management and User Behavior
paper · pdf · doi:10.48550/arxiv.2503.08961
openalex publication_date 2025/03/11 · openalex created_date 2025/10/13 · openalex updated_date 2026/07/28
Single-player contextual bandits are a well-studied problem in reinforcement learning that has seen applications in various fields such as advertising, healthcare, and finance. In light of the recent work on information asymmetric bandits \citechang2022online, chang2023online, we propose a novel multiplayer information asymmetric contextual bandit framework where there are multiple players each with their own set of actions. At every round, they observe the same context vectors and simultaneously take an action from their own set of actions, giving rise to a joint action. However, upon taking this action the players are subjected to information asymmetry in (1) actions and/or (2) rewards. We designed an algorithm LinUCB by modifying the classical single-player algorithm LinUCB in \citechu2011contextual to achieve the optimal regret O(√(T)) when only one kind of asymmetry is present. We then propose a novel algorithm ETC that is built on explore-then-commit principles to achieve the same optimal regret when both types of asymmetry are present.