{"total":20,"rows":[{"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":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"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":"2205.04134","title":"Federated Multi-Armed Bandits Under Byzantine Attacks","created":"2022-05-09","cited_by_count":6,"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":"2305.18784","title":"Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits","created":"2023-05-30","cited_by_count":4,"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":"2310.07320","title":"Byzantine-Resilient Decentralized Multi-Armed Bandits","created":"2023-10-11","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":"2210.12198","title":"Anonymous Bandits for Multi-User Systems","created":"2022-10-21","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":"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":"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":"2305.19161","title":"Cooperative Thresholded Lasso for Sparse Linear Bandit","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2311.01698","title":"Adversarial Attacks on Cooperative Multi-agent Bandits","created":"2023-11-03","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}],"next_cursor":null}