paper-with-me

홈 › Papers

Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem

2015-06-08 · Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that the proposed algorithm significantly outperforms existing ones.

📄 PDF Abstract BibTeX arXiv:1506.02550

Code (1)

jkomiyama/duelingbanditlib 공식 구현

Similar Papers 제목 키워드 기반

Regret Analysis for Continuous Dueling Bandit

2017-11-21 · NeurIPS 2017 12 · Wataru Kumagai

The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem bas…

Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm

2016-05-05 · Junpei Komiyama, Junya Honda, Hiroshi Nakagawa

We study the K-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. The hardness of recommending Copeland winners, t…

Borda Regret Minimization for Generalized Linear Dueling Bandits

2023-03-15 · Yue Wu, Tao Jin, Hao Lou, Farzad Farnoud 외

Dueling bandits are widely used to model preferential feedback prevalent in many applications such as recommendation systems and ranking. In this paper, we study the Borda regret minimization problem for dueling bandits,…

Recommendation Systems

Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives

2026-03-19 · S Akash, Pratik Gajane, Jawar Singh arxiv

Multi-dueling bandits, where a learner selects $m \geq 2$ arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation systems, yet a fundamental question has rem…

Recommendation Systems

Adversarial Multi-dueling Bandits

2024-06-18 · Pratik Gajane

We introduce the problem of regret minimization in adversarial multi-dueling bandits. While adversarial preferences have been studied in dueling bandits, they have not been explored in multi-dueling bandits. In this sett…