Dueling Bandits

Follow this topic Ask about this topic

Latest papers

17 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Conservative Dueling Bandits: Preference Learning under Baseline Constraints
Oct 27, 2026Rohan Deb, Mohammad Ghavamzadeh, Arindam BanerjeeDueling Bandits Contextual Bandits
University of Illinois, Urbana Champaign · Qualcomm AI Research
Conversational Generalized Linear Bandits with Hybrid Feedback
Oct 26, 2026Yurui Zou, Qirun Zeng, Jinhang ZuoBandit Learning Contextual Bandits
University of Science and Technology of China, Hefei, China · City University of Hong Kong, Hong Kong SAR, China
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
Oct 17, 2026Jie Mao, Pingchen Lu, Xiangyi Wang +4LLM Personalization User Preference Modeling
The Chinese University of Hong Kong, Shenzhen · University of Copenhagen · City University of Hong Kong +1
Replicable Dueling Bandits
Oct 14, 2026Rohan Deb, Aadirupa Saha, Udaya Ghai +2Dueling Bandits Multi-Armed Bandits
University of Illinois, Urbana Champaign · University of Illinois, Chicago · Amazon +1
Cost-Aware Best-LLM Identification using Dueling Feedback
Sep 24, 2026Sarvesh Gharat, Nikhil Karamchandani, Jayakrishnan NairDueling Bandits Best-Arm Identification
Centre for Machine Intelligence and Data Science (C-MInDS) Indian Institute of Technology Bombay · Department of Electrical Engineering Indian Institute of Technology Bombay
Optimal Top- $k$ Identification from Pairwise Comparisons
Jul 9, 2026Motti Goldberger, Nils RudiPairwise Preference Learning Multi-Armed Bandits
Yale University, New Haven, CT, USA.
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
Jun 1, 2026Pu Wang, Yao-Xiang DingMulti-Armed Bandits Best-Arm Identification
State Key Lab of CAD&CG, Zhejiang University
CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
May 30, 2026Son Nguyen, Xinyuan Liu, Ransalu SenanayakeMulti-Armed Bandits Dueling Bandits
School of Computing and Augmented Intelligence, Arizona State University, Tempe, United States of America
Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
May 10, 2026Soumita Hait, Ping Li, Haipeng Luo +1Last-Iterate Convergence Imperfect-Information Games
University of Southern California · Shanghai University of Finance and Economics · University of Iowa
Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
May 7, 2026Qirun Zeng, Xuchuang Wang, Jiayi Shen +3Multi-Armed Bandits Best-Arm Identification
Department of Computer Science City University of Hong Kong, Hong Kong SAR, China · Manning College of Information & Computer Science University of Massachusetts Amherst, Amherst, MA, USA · School of Management University of Science and Technology of China, Hefei, Anhui, China +3
Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare
May 3, 2026Maheed H. Ahmed, Mahsa GhasemiPairwise Preference Learning Multi-Armed Bandits
Electrical and Computer Engineering Purdue University
Analysis of Search Heuristics in the Multi-Armed Bandit Setting
Apr 9, 2026Jasmin Brandt, Barbara Hammer, Timo Kötzing +1Dueling Bandits Multi-Armed Bandits
University of Bielefeld Bielefeld, Germany · Hasso Plattner Institute University of Potsdam Potsdam, Germany
Lipschitz Dueling Bandits over Continuous Action Spaces
Apr 1, 2026Mudit Sharma, Shweta Jain, Vaneet Aggarwal +1Lipschitz Bandits Dueling Bandits
Indian Institute of Technology Ropar · Purdue University · Indian Institute of Technology Hyderabad
Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
Mar 19, 2026S Akash, Pratik Gajane, Jawar SinghBest-of-Both-Worlds Bandits Dueling Bandits
Indian Institute of Technology Patna, India · University of Orléans, France
The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
Mar 16, 2026El Mehdi Saad, Victor Thuot, Nicolas VerzelenDueling Bandits Best-Arm Identification
CC-UM6P-Rabat · INRAE, MISTEA, Institut Agro, Univ. Montpellier Montpellier, France · MISTEA +1
PARWiS: Winner determination under shoestring budgets using active pairwise comparisons
Mar 1, 2026Shailendra BhandariDueling Bandits Pairwise Preference Learning
Department of Computer Science OsloMet– Oslo Metropolitan University Oslo, Norway
From Dueling Bandits to Episodic MDPs: Learning with Adversarial Preference Feedback
Jul 15, 2025Taira Tsuchiya, Shinji Ito, Haipeng LuoPreference-Based RL Dueling Bandits
The University of Tokyo and RIKEN · University of Southern California

Oct 27, 2026J/K move · Enter open · S save

Conservative Dueling Bandits: Preference Learning under Baseline Constraints

Rohan Deb, Mohammad Ghavamzadeh, Arindam Banerjee

University of Illinois, Urbana Champaign · Qualcomm AI Research

Dueling Bandits Contextual Bandits

Open paper AskPDF arXiv

Contextual dueling bandits learn from pairwise comparisons, the same feedback used to fine-tune language models from human preferences. Standard algorithms explore aggressively and can show users two poor options. We study conservative contextual dueling bandits, which require that, at every round, the cumulative score of the better displayed item stay above a

(1-α)

fraction of a trusted baseline's. An item's score is its probability of beating the best available item, so the constraint depends only on utility differences and needs no absolute rewards. This also changes how safety can be certified: we show that transferring the safety test of the conservative bandit algorithm CLUCB unchanged can incur linear regret, even when the baseline's utilities are known exactly. For linear utilities, we develop MaxInP-BC, which certifies scores through utility gaps and, when it must fall back, pairs the baseline with an informative partner so that fallback rounds still drive learning. It is safe with high probability at all times, with regret

\tilde{O}(d\sqrt{T}/κ)

plus an additive cost of conservatism that does not grow with the horizon. For general utility classes, we develop BTIGW-BC, which turns the guarantee of an online logistic-regression oracle into cumulative safety certificates. It is safe at all times, makes finitely many fallbacks, and has sublinear regret whenever the oracle's logistic regret is sublinear. In experiments, both satisfy the constraint, which their unconstrained counterparts often violate, at a moderate cost in regret.