多玩家博弈中解决行动与收益信息不对称问题，实现最优后悔率。
Multiplayer Information Asymmetric Contextual Bandits
- 扩展单玩家线性上下文老虎机，支持多玩家与双类信息不对称。
- 在仅一种不对称时，算法实现 $O(\sqrt{T})$ 的最优后悔率。
- 提出探索-承诺框架新算法，适用于两类不对称场景。
单玩家上下文老虎机是强化学习中研究充分的问题，已广泛应用于广告、医疗和金融等领域。针对近期提出的‘信息不对称’老虎机工作，本文提出一种新型多玩家信息不对称上下文老虎机框架，其中多个玩家各自拥有独立的动作集。每轮中，他们观察相同的上下文向量，并从各自动作集中同时采取动作，形成联合动作。但执行后，玩家在（1）动作和/或（2）奖励上面临信息不对称。我们通过修改经典单玩家算法 exttt{LinUCB}，设计出 exttt{LinUCB} 算法，在仅存在一类不对称时达到最优后悔率 $O(\sqrt{T})$。随后提出基于探索-承诺原则的新算法 exttt{ETC}，在两类不对称同时存在时仍能实现相同的最优后悔率。
原文摘要 · Abstract (English)
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 \emph{information asymmetric} bandits \cite{chang2022online, 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 \texttt{LinUCB} by modifying the classical single-player algorithm \texttt{LinUCB} in \cite{chu2011contextual} to achieve the optimal regret $O(\sqrt{T})$ when only one kind of asymmetry is present. We then propose a novel algorithm \texttt{ETC} that is built on explore-then-commit principles to achieve the same optimal regret when both types of asymmetry are present.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。