{"total":47,"rows":[{"id":"2102.08462","title":"Multi-Agent Multi-Armed Bandits with Limited Communication","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"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":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2205.13170","title":"Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost","created":"2022-05-26","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":"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":"2205.14174","title":"Private and Byzantine-Proof Cooperative Decision-Making","created":"2022-05-27","cited_by_count":10,"area":null},{"id":"2209.11817","title":"An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret","created":"2022-09-23","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":"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":"2302.07446","title":"On-Demand Communication for Asynchronous Multi-Agent Bandits","created":"2023-02-15","cited_by_count":7,"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":"2209.09624","title":"Robust Online and Distributed Mean Estimation Under Adversarial Data Corruption","created":"2022-09-17","cited_by_count":5,"area":null},{"id":"2101.04306","title":"Multi-Robot Gaussian Process Estimation and Coverage: A Deterministic Sequencing Algorithm and Regret Analysis","created":"2021-01-12","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":"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":"2211.17154","title":"On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits","created":"2022-11-30","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":"2212.06279","title":"Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits","created":"2022-12-12","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":"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":"2308.08046","title":"Regret Lower Bounds in Multi-agent Multi-armed Bandit","created":"2023-08-15","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":"2402.04417","title":"Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2410.23867","title":"QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.12154","title":"Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2501.03132","title":"Communication Bounds for the Distributed Experts Problem","created":"2025-01-06","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":"2605.27073","title":"Learning to Orchestrate Agents under Uncertainty","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2306.08670","title":"Simple Opinion Dynamics for No-Regret Learning","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2312.04719","title":"Distributed Optimization via Kernelized Multi-armed Bandits","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2408.10865","title":"Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities","created":"2024-08-20","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":"2506.15943","title":"On the optimal regret of collaborative personalized linear bandits","created":"2025-06-19","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":"2603.11757","title":"Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach","created":"2026-03-12","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":"2608.11873","title":"DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}