paper-with-me

홈 › Papers

Best of both worlds: Stochastic & adversarial best-arm identification

2026-04-16 · Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko arxiv

We study bandit best-arm identification with arbitrary and potentially adversarial rewards. A simple random uniform learner obtains the optimal rate of error in the adversarial scenario. However, this type of strategy is suboptimal when the rewards are sampled stochastically. Therefore, we ask: Can we design a learner that performs optimally in both the stochastic and adversarial problems while not being aware of the nature of the rewards? First, we show that designing such a learner is impossible in general. In particular, to be robust to adversarial rewards, we can only guarantee optimal rates of error on a subset of the stochastic problems. We give a lower bound that characterizes the optimal rate in stochastic problems if the strategy is constrained to be robust to adversarial rewards. Finally, we design a simple parameter-free algorithm and show that its probability of error matches (up to log factors) the lower bound in stochastic problems, and it is also robust to adversarial ones.

📄 PDF Abstract BibTeX arXiv:2604.14860

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Blackbox Approach to Best of Both Worlds in Bandits and Beyond

2023-02-20 · Christoph Dann, Chen-Yu Wei, Julian Zimmert

Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both the adversarial and the stochastic regimes have received growing attention recently. Existing techniques often require careful …

Multi-Armed Bandits

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback

2024-10-03 · Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi 외

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-wo…

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback

2025-05-30 · Ofir Schlisselberg, Tal Lancewicki, Peter Auer, Yishay Mansour

We study the multi-armed bandit problem with adversarially chosen delays in the Best-of-Both-Worlds (BoBW) framework, which aims to achieve near-optimal performance in both stochastic and adversarial environments. While …

Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits

2022-01-28 · Jiatai Huang, Yan Dai, Longbo Huang

In this paper, we generalize the concept of heavy-tailed multi-armed bandits to adversarial environments, and develop robust best-of-both-worlds algorithms for heavy-tailed multi-armed bandits (MAB), where losses have $\…

Multi-Armed Bandits

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits

2023-12-24 · Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale 외

We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and stochastic regimes, without prior knowledge about the environ…

Multi-Armed Bandits