{"total":52,"rows":[{"id":"2108.08843","title":"Learning Equilibria in Matching Markets from Bandit Feedback","created":"2021-08-19","cited_by_count":34,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2106.02553","title":"Fair Exploration via Axiomatic Bargaining","created":"2021-06-04","cited_by_count":22,"area":null},{"id":"2208.14423","title":"Competition, Alignment, and Equilibria in Digital Marketplaces","created":"2022-08-30","cited_by_count":17,"area":null},{"id":"2112.06283","title":"Bayesian Persuasion for Algorithmic Recourse","created":"2021-12-12","cited_by_count":14,"area":null},{"id":"2403.03811","title":"Incentivized Learning in Principal-Agent Bandit Games","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2102.10156","title":"Learning to Persuade on the Fly: Robustness Against Ignorance","created":"2021-02-19","cited_by_count":12,"area":null},{"id":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2203.13423","title":"Modeling Attrition in Recommender Systems with Departing Bandits","created":"2022-03-25","cited_by_count":11,"area":null},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2306.06250","title":"Strategic Apple Tasting","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2206.00494","title":"Incentivizing Combinatorial Bandit Exploration","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2402.04971","title":"Multi-Sender Persuasion: A Computational Perspective","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2201.12408","title":"Networked Restless Multi-Armed Bandits for Mobile Interventions","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2302.07425","title":"Bandit Social Learning: Exploration under Myopic Behavior","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2104.03860","title":"Incentivizing Exploration in Linear Bandits under Information Gap","created":"2021-04-08","cited_by_count":5,"area":null},{"id":"2105.04976","title":"Designing an Automatic Agent for Repeated Language based Persuasion Games","created":"2021-05-11","cited_by_count":5,"area":null},{"id":"2110.12160","title":"Multi-armed Bandit Algorithm against Strategic Replication","created":"2021-10-23","cited_by_count":5,"area":null},{"id":"2211.15381","title":"Incentive-Aware Recommender Systems in Two-Sided Markets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2306.01990","title":"Incentivizing Exploration with Linear Contexts and Combinatorial Actions","created":"2023-06-03","cited_by_count":5,"area":null},{"id":"2406.00551","title":"Strategic Linear Contextual Bandits","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2509.11265","title":"SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing","created":"2025-09-14","cited_by_count":5,"area":null},{"id":"2107.10093","title":"Incentivizing Compliance with Algorithmic Instruments","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2205.06331","title":"Collaborative Multi-agent Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2110.03068","title":"Learning the Optimal Recommendation from Explorative Users","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2110.14628","title":"(Almost) Free Incentivized Exploration from Decentralized Learning Agents","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2202.01879","title":"Learning from a Learning User for Optimal Recommendations","created":"2022-02-03","cited_by_count":3,"area":null},{"id":"2306.10606","title":"Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces","created":"2023-06-18","cited_by_count":3,"area":null},{"id":"2312.07929","title":"Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2403.10819","title":"Incentivized Exploration of Non-Stationary Stochastic Bandits","created":"2024-03-16","cited_by_count":3,"area":null},{"id":"2105.08869","title":"Incentivized Bandit Learning with Self-Reinforcing User Preferences","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2403.00845","title":"Improved Online Learning Algorithms for CTR Prediction in Ad Auctions","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2508.19466","title":"Incentivized Lipschitz Bandits","created":"2025-08-26","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":"2402.14013","title":"Misalignment, Learning, and Ranking: Harnessing Users Limited Attention","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2406.04374","title":"Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender System","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.17086","title":"Exploration and Persuasion","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2501.03865","title":"Truthful mechanisms for linear bandit games with private contexts","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2109.12445","title":"Algorithmic Information Design in Multi-Player Games: Possibility and Limits in Singleton Congestion","created":"2021-09-25","cited_by_count":0,"area":null},{"id":"2305.02441","title":"Reward Teaching for Federated Multi-armed Bandits","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2311.00260","title":"Incentivized Collaboration in Active Learning","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2312.16307","title":"Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2410.03651","title":"Minimax-optimal trust-aware multi-armed bandits","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2502.15338","title":"Learning with Limited Shared Information in Multi-agent Multi-armed Bandit","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2503.20975","title":"Competitive Multi-armed Bandit Games for Resource Sharing","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2506.01685","title":"Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2602.20465","title":"Prior-Agnostic Incentive-Compatible Exploration","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.13145","title":"Collaborating in Multi-Armed Bandits with Strategic Agents","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.18300","title":"On Incentivized Exploration beyond Bayesianism and Full-Information","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}