{"total":56,"rows":[{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2108.08843","title":"Learning Equilibria in Matching Markets from Bandit Feedback","created":"2021-08-19","cited_by_count":34,"area":null},{"id":"2103.07501","title":"Beyond $\\log^2(T)$ Regret for Decentralized Bandits in Matching Markets","created":"2021-03-12","cited_by_count":30,"area":null},{"id":"2102.06246","title":"Regret, stability & fairness in matching markets with bandit learners","created":"2021-02-11","cited_by_count":20,"area":null},{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2307.10890","title":"Player-optimal Stable Regret for Bandit Learning in Matching Markets","created":"2023-07-20","cited_by_count":17,"area":null},{"id":"2203.03684","title":"Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2107.03427","title":"Deep Learning for Two-Sided Matching","created":"2021-07-07","cited_by_count":15,"area":null},{"id":"2102.06988","title":"Learning in Multi-Stage Decentralized Matching Markets","created":"2021-02-13","cited_by_count":12,"area":null},{"id":"2206.02344","title":"Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2204.12048","title":"Thompson Sampling for Bandit Learning in Matching Markets","created":"2022-04-26","cited_by_count":10,"area":null},{"id":"2204.13502","title":"Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications","created":"2022-04-28","cited_by_count":10,"area":null},{"id":"2106.04228","title":"Decentralized Learning in Online Queuing Systems","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2309.06375","title":"Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2401.01528","title":"Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2410.04376","title":"Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning","created":"2024-10-06","cited_by_count":7,"area":null},{"id":"2305.19158","title":"Competing for Shareable Arms in Multi-Player Multi-Armed Bandits","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2408.08690","title":"Explore-then-Commit Algorithms for Decentralized Two-Sided Matching Markets","created":"2024-08-16","cited_by_count":6,"area":null},{"id":"2206.00120","title":"Decentralized Competing Bandits in Non-Stationary Matching Markets","created":"2022-05-31","cited_by_count":5,"area":null},{"id":"2301.10230","title":"Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints","created":"2023-01-24","cited_by_count":5,"area":null},{"id":"2501.03018","title":"Probably Correct Optimal Stable Matching for Two-Sided Markets Under Uncertainty","created":"2025-01-06","cited_by_count":5,"area":null},{"id":"2305.18784","title":"Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2502.10826","title":"Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2506.15926","title":"Competing Bandits in Matching Markets via Super Stability","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2106.03927","title":"Improving Social Welfare While Preserving Autonomy via a Pareto Mediator","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2210.11692","title":"Competing Bandits in Time Varying Matching Markets","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2406.14784","title":"Active Learning for Fair and Stable Online Allocations","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2503.08004","title":"Multiplayer Information Asymmetric Bandits in Metric Spaces","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2503.08961","title":"Multiplayer Information Asymmetric Contextual Bandits","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2411.03270","title":"Stable Matching with Ties: Approximation Ratios and Learning","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2412.00301","title":"Bandit Learning in Matching Markets: Utilitarian and Rawlsian Perspectives","created":"2024-11-30","cited_by_count":2,"area":null},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2607.04824","title":"Probably Correct Optimal Stable Matching under Two-Sided Uncertainty","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2212.06891","title":"Interactive Learning with Pricing for Optimal and Stable Allocations in Markets","created":"2022-12-13","cited_by_count":1,"area":null},{"id":"2309.10594","title":"Decentralized Online Learning in Task Assignment Games for Mobile Crowdsensing","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2411.11794","title":"Competing Bandits in Decentralized Contextual Matching Markets","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2505.07688","title":"Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2512.06758","title":"Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2603.19700","title":"Regret Analysis of Sleeping Competing Bandits","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.28290","title":"Adaptive Bandit Algorithms for Contextual Matching Markets","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2105.02589","title":"Bandit based centralized matching in two-sided markets for peer to peer lending","created":"2021-05-06","cited_by_count":0,"area":null},{"id":"2207.04143","title":"Interactive Recommendations for Optimal Allocations in Markets with Constraints","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2208.06536","title":"Double Auctions with Two-sided Bandit Feedback","created":"2022-08-13","cited_by_count":0,"area":null},{"id":"2306.04498","title":"Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Bandits","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2403.15524","title":"PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2409.04897","title":"Centralized Selection with Preferences in the Presence of Biases","created":"2024-09-07","cited_by_count":0,"area":null},{"id":"2506.03802","title":"Learning in Matching Games with Bandit Feedback","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.20039","title":"Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.04194","title":"Stochastic Matching Bandits with Rare Optimization Updates","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.09425","title":"Bandits with Single-Peaked Preferences and Limited Resources","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.16183","title":"Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedback","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2605.03216","title":"MenuNet: A Strategy-Proof Mechanism for Matching Markets","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.19883","title":"Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.29221","title":"A Linear Matching Bandit Approach to Online Multi-Human Multi-Robot Teaming","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2609.19963","title":"Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.12960","title":"DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}