paper-with-me

홈 › Papers

Continuous-in-time Limit for Bayesian Bandits

2022-10-14 · Yuhua Zhu, Zachary Izzo, Lexing Ying

This paper revisits the bandit problem in the Bayesian setting. The Bayesian approach formulates the bandit problem as an optimization problem, and the goal is to find the optimal policy which minimizes the Bayesian regret. One of the main challenges facing the Bayesian approach is that computation of the optimal policy is often intractable, especially when the length of the problem horizon or the number of arms is large. In this paper, we first show that under a suitable rescaling, the Bayesian bandit problem converges toward a continuous Hamilton-Jacobi-Bellman (HJB) equation. The optimal policy for the limiting HJB equation can be explicitly obtained for several common bandit problems, and we give numerical methods to solve the HJB equation when an explicit solution is not available. Based on these results, we propose an approximate Bayes-optimal policy for solving Bayesian bandit problems with large horizons. Our method has the added benefit that its computational cost does not increase as the horizon increases.

📄 PDF Abstract BibTeX arXiv:2210.07513

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Overcoming Free-Riding in Bandit Games

2019-10-20 · Johannes Hörner, Nicolas Klein, Sven Rady

This paper considers a class of experimentation games with L\'{e}vy bandits encompassing those of Bolton and Harris (1999) and Keller, Rady and Cripps (2005). Its main result is that efficient (perfect Bayesian) equilibr…

Bayesian Optimisation over Multiple Continuous and Categorical Inputs

2019-06-20 · ICML 2020 1 · Binxin Ru, Ahsan S. Alvi, Vu Nguyen, Michael A. Osborne 외

Efficient optimisation of black-box problems that comprise both continuous and categorical inputs is important, yet poses significant challenges. We propose a new approach, Continuous and Categorical Bayesian Optimisatio…

Bayesian OptimisationDiversityMulti-Armed Bandits

An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces

2025-02-04 · Amaury Gouverneur, Borja Rodriguez Gálvez, Tobias Oechtering, Mikael Skoglund

This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015). Specifically, it extends the rate-dis…

Thompson Sampling

KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

2025-02-11 · Jusheng Zhang, Zimeng Huang, Yijia Fan, Ningyuan Liu 외

As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-…

Thompson Sampling

Lipschitz Dueling Bandits over Continuous Action Spaces

2026-04-01 · Mudit Sharma, Shweta Jain, Vaneet Aggarwal, Ganesh Ghalme arxiv

We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separate…