{"total":48,"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":"2102.08462","title":"Multi-Agent Multi-Armed Bandits with Limited Communication","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2207.03106","title":"A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits","created":"2022-07-07","cited_by_count":28,"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":"2105.01798","title":"Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence","created":"2021-05-04","cited_by_count":18,"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":"2111.01570","title":"Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits","created":"2021-11-02","cited_by_count":11,"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":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2201.09353","title":"Distributed Bandits with Heterogeneous Agents","created":"2022-01-23","cited_by_count":9,"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":"2211.02212","title":"Distributed Linear Bandits under Communication Constraints","created":"2022-11-04","cited_by_count":8,"area":null},{"id":"2302.07446","title":"On-Demand Communication for Asynchronous Multi-Agent Bandits","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2207.07948","title":"Collaborative Learning in Kernel-based Bandits for Distributed Users","created":"2022-07-16","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":"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":"2404.06460","title":"Learning Locally Interacting Discrete Dynamical Systems: Towards Data-Efficient and Scalable Prediction","created":"2024-04-09","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":"2507.11891","title":"Choosing the Better Bandit Algorithm under Data Sharing: When Do A/B Experiments Work?","created":"2025-07-16","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":"2204.12371","title":"Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning","created":"2022-04-26","cited_by_count":3,"area":null},{"id":"2308.04314","title":"Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2309.11702","title":"Incentivized Communication for Federated Bandits","created":"2023-09-21","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":"2406.19824","title":"Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality","created":"2024-06-28","cited_by_count":3,"area":null},{"id":"2109.09427","title":"Asymptotic Optimality for Decentralised Bandits","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2212.06279","title":"Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits","created":"2022-12-12","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":"2502.08003","title":"Heterogeneous Multi-agent Multi-armed Bandits on Stochastic Block Models","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2110.00751","title":"Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams","created":"2021-10-02","cited_by_count":1,"area":null},{"id":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","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":"2312.15549","title":"Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2401.10383","title":"Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2408.03405","title":"Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2605.06864","title":"Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2201.01182","title":"Modelling Cournot Games as Multi-agent Multi-armed Bandits","created":"2022-01-01","cited_by_count":0,"area":null},{"id":"2201.12482","title":"Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability","created":"2022-01-29","cited_by_count":0,"area":null},{"id":"2203.00076","title":"Robust Multi-Agent Bandits Over Undirected Graphs","created":"2022-02-28","cited_by_count":0,"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":"2306.08670","title":"Simple Opinion Dynamics for No-Regret Learning","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2402.13182","title":"Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness","created":"2024-02-20","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":"2506.10313","title":"Collaborative Min-Max Regret in Grouped Multi-Armed Bandits","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2510.22811","title":"Distributed Multi-Agent Bandits Over Erd\\H{o}s-R\\'enyi Random Networks","created":"2025-10-26","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":"2605.06202","title":"Bandit Learning in General Open Multi-agent Systems","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}