{"total":38,"rows":[{"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":"2109.05700","title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","created":"2021-09-13","cited_by_count":20,"area":null},{"id":"2111.12482","title":"One More Step Towards Reality: Cooperative Bandits with Imperfect Communication","created":"2021-11-24","cited_by_count":15,"area":null},{"id":"2111.00781","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2201.04805","title":"Non-Stationary Representation Learning in Sequential Linear Bandits","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2306.05579","title":"Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards","created":"2023-06-08","cited_by_count":11,"area":null},{"id":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2110.04396","title":"When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits","created":"2021-10-08","cited_by_count":8,"area":null},{"id":"2305.12795","title":"Bandit Submodular Maximization for Multi-Robot Coordination in Unpredictable and Partially Observable Environments","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2106.04207","title":"Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2110.07392","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2206.02834","title":"Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds","created":"2022-06-06","cited_by_count":5,"area":null},{"id":"2208.11530","title":"Collaborative Algorithms for Online Personalized Mean Estimation","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","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":"2111.10933","title":"Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2310.07320","title":"Byzantine-Resilient Decentralized Multi-Armed Bandits","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2207.14391","title":"Distributed Stochastic Bandit Learning with Delayed Context Observation","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2306.05998","title":"Distributed Consensus Algorithm for Decision-Making in Multi-agent Multi-armed Bandit","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2410.17382","title":"Cooperative Multi-Agent Constrained Stochastic Linear Bandits","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2502.08003","title":"Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Models","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2205.05820","title":"Representation Learning for Context-Dependent Decision-Making","created":"2022-05-12","cited_by_count":1,"area":null},{"id":"2303.17043","title":"Federated Learning for Heterogeneous Bandits with Unobserved Contexts","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2308.08046","title":"Regret Lower Bounds in Multi-agent Multi-armed Bandit","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2402.04417","title":"Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2407.09124","title":"Decentralized multi-agent reinforcement learning algorithm using a cluster-synchronized laser network","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2510.00602","title":"Multi-Agent Stage-wise Conservative Linear Bandits","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2602.16965","title":"Multi-Agent Lipschitz Bandits","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2303.05445","title":"Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2309.16161","title":"Leveraging Untrustworthy Commands for Multi-Robot Coordination in Unpredictable Environments: A Bandit Submodular Maximization Approach","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2403.11603","title":"Fair Distributed Cooperative Bandit Learning on Networks for Intelligent Internet of Things Systems (Technical Report)","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2404.04509","title":"Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2406.18072","title":"Learning for Bandits under Action Erasures","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2605.06202","title":"Bandit Learning in General Open Multi-agent Systems","created":"2026-05-07","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":"2605.27076","title":"Cost of Structural Learning Under Censored Feedback: A Threshold-Bandit Approach","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.22120","title":"The Price of Decentralization in Top-$K$ Arm Identification","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}