paper-with-me

홈 › Papers

Sleeping Combinatorial Bandits

2021-06-03 · Kumar Abhishek, Ganesh Ghalme, Sujit Gujar, Yadati Narahari

In this paper, we study an interesting combination of sleeping and combinatorial stochastic bandits. In the mixed model studied here, at each discrete time instant, an arbitrary \emph{availability set} is generated from a fixed set of \emph{base} arms. An algorithm can select a subset of arms from the \emph{availability set} (sleeping bandits) and receive the corresponding reward along with semi-bandit feedback (combinatorial bandits). We adapt the well-known CUCB algorithm in the sleeping combinatorial bandits setting and refer to it as \CSUCB. We prove -- under mild smoothness conditions -- that the \CSUCB\ algorithm achieves an $O(\log (T))$ instance-dependent regret guarantee. We further prove that (i) when the range of the rewards is bounded, the regret guarantee of \CSUCB\ algorithm is $O(\sqrt{T \log (T)})$ and (ii) the instance-independent regret is $O(\sqrt[3]{T^2 \log(T)})$ in a general setting. Our results are quite general and hold under general environments -- such as non-additive reward functions, volatile arm availability, a variable number of base-arms to be pulled -- arising in practical applications. We validate the proven theoretical guarantees through experiments.

📄 PDF Abstract BibTeX arXiv:2106.01624

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Worst-Case Regret Bounds for Combinatorial Thompson Sampling in Sleeping Semi-Bandits

2026-05-10 · Zhiming Huang, Bingshan Hu, Jianping Pan arxiv

We revisit combinatorial Thompson sampling (CTS) for semi-bandits with sleeping arms, where arm availability varies over time and actions must satisfy combinatorial constraints, as in wireless mesh routing with fluctuati…

Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints

2020-05-14 · Zhiming Huang, Yifan Xu, Bingshan Hu, QiPeng Wang 외

We study the combinatorial sleeping multi-armed semi-bandit problem with long-term fairness constraints~(CSMAB-F). To address the problem, we adopt Thompson Sampling~(TS) to maximize the total rewards and use virtual que…

FairnessMovie RecommendationThompson Sampling

One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits

2022-10-26 · Pierre Gaillard, Aadirupa Saha, Soham Dan

We address the problem of \emph{`Internal Regret'} in \emph{Sleeping Bandits} in the fully adversarial setup, as well as draw connections between different existing notions of sleeping regrets in the multiarmed bandits (…

Dueling Bandits with Adversarial Sleeping

2021-07-05 · NeurIPS 2021 12 · Aadirupa Saha, Pierre Gaillard

We introduce the problem of sleeping dueling bandits with stochastic preferences and adversarial availabilities (DB-SPAA). In almost all dueling bandit applications, the decision space often changes over time; eg, retail…

ManagementMulti-Armed Bandits

Near-optimal Per-Action Regret Bounds for Sleeping Bandits

2024-03-02 · Quan Nguyen, Nishant A. Mehta

We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ …