paper-with-me

Papers

Neural Dueling Bandits: Preference-Based Optimization with Human Feedback

2024-07-24 · Arun Verma, Zhongxiang Dai, Xiaoqiang Lin, Patrick Jaillet, Bryan Kian Hsiang Low

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However, existing algorithms assume the reward function is linear, which can be complex and non-linear in many real-life applications like online recommendations or ranking web search results. To overcome this challenge, we use a neural network to estimate the reward function using preference feedback for the previously selected arms. We propose upper confidence bound- and Thompson sampling-based algorithms with sub-linear regret guarantees that efficiently select arms in each round. We also extend our theoretical results to contextual bandit problems with binary feedback, which is in itself a non-trivial contribution. Experimental results on the problem instances derived from synthetic datasets corroborate our theoretical results.

📄 PDF Abstract BibTeX arXiv:2407.17112

Code (0)

등록된 구현이 없습니다.

Tasks

Thompson Sampling

Similar Papers 제목 키워드 기반

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

Multi-dueling Bandits with Dependent Arms

2017-04-29 · Yanan Sui, Vincent Zhuang, Joel W. Burdick, Yisong Yue

The dueling bandits problem is an online learning framework for learning from pairwise preference feedback, and is particularly well-suited for modeling settings that elicit subjective or implicit human feedback. In this…

Thompson Sampling

Linear and Neural Dueling Bandits with Delayed Feedback

2026-05-26 · Xiangyi Wang, Pingchen Lu, Jie Mao, Mingze Kong 외 arxiv

Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in recommender systems and large language model alignment. However, standard algorithms rely on the idealized …

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…

Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback

2025-11-12 · Shengbo Wang, Hong Sun, Ke Li arxiv

Interactive preference elicitation (IPE) aims to substantially reduce human effort while acquiring human preferences in wide personalization systems. Dueling bandit (DB) algorithms enable optimal decision-making in IPE b…