{"total":36,"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":"2102.06246","title":"Regret, stability & fairness in matching markets with bandit learners","created":"2021-02-11","cited_by_count":20,"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":"2111.12482","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":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","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":"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":"2206.02834","title":"Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds","created":"2022-06-06","cited_by_count":5,"area":null},{"id":"2106.04982","title":"Cooperative Online Learning with Feedback Graphs","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2305.18784","title":"Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits","created":"2023-05-30","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":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2301.11442","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","created":"2023-01-26","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":"2310.07320","title":"Byzantine-Resilient Decentralized Multi-Armed Bandits","created":"2023-10-11","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":"2405.16168","title":"Multi-Player Approaches for Dueling Bandits","created":"2024-05-25","cited_by_count":2,"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":"2201.01182","title":"Modelling Cournot Games as Multi-agent Multi-armed Bandits","created":"2022-01-01","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":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","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":"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":"2506.10313","title":"Collaborative Min-Max Regret in Grouped Multi-Armed Bandits","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2510.06683","title":"Distributed Algorithms for Multi-Agent Multi-Armed Bandits with Collision","created":"2025-10-08","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},{"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":"2610.06062","title":"Pay to Learn, Share to Earn: Incentivized Federated Multi-Player Bandits","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}