{"total":19,"rows":[{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2110.14622","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2109.03818","title":"Online Learning for Cooperative Multi-Player Multi-Armed Bandits","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2311.06210","title":"Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2112.11818","title":"Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2407.00575","title":"Learning to Control Unknown Strongly Monotone Games","created":"2024-06-30","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":"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":"2111.12581","title":"Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2209.05408","title":"Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning","created":"2022-09-12","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":"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":"2202.11699","title":"Exploiting Side Information for Improved Online Learning Algorithms in Wireless Networks","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2306.04498","title":"Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Bandits","created":"2023-06-07","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":"2512.17161","title":"Distributed Learning in Markovian Restless Bandits over Interference Graphs for Stable Spectrum Sharing","created":"2025-12-19","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}