mlsanityData to 7 Oct 2026

SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits

arXiv 1809.08151 ↗First posted 21 Sep 2018cs.LG stat.MLcited by 46

Not on the map. Why?

Abstract (arXiv)

Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at the same stage. We present a decentralized algorithm that achieves the same performance as a centralized one, contradicting the existing lower bounds for that problem. This is possible by "hacking" the standard model by constructing a communication protocol between players that deliberately enforces collisions, allowing them to share their information at a negligible cost. This motivates the introduction of a more appropriate dynamic setting without sensing, where similar communication protocols are no longer possible. However, we show that the logarithmic growth of the regret is still achievable for this model with a new algorithm.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 9; 2024: 6; 2025: 4; 2026: 5.

46 papers.

Sort:

  1. 2021Federated Multi-armed Bandits with Personalizationcited by 62
  2. 2021Federated Linear Contextual Banditscited by 61
  3. 2021Federated Multi-Armed Banditscited by 59
  4. 2021Beyond log2(T) Regret for Decentralized Bandits in Matching Marketscited by 29
  5. 2021Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalizationcited by 18
  6. 2022A survey on multi-player banditscited by 18
  7. 2021Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Informationcited by 11
  8. 2022Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applicationscited by 10
  9. 2022Federated Online Clustering of Banditscited by 10
  10. 2022Distributed Bandits with Heterogeneous Agentscited by 9
  11. 2021Multi-player Multi-armed Bandits with Collision-Dependent Reward Distributionscited by 8
  12. 2023Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communicationcited by 8
34 more
  1. 2021Decentralized Learning in Online Queuing Systemscited by 7
  2. 2021An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Banditcited by 6
  3. 2023On-Demand Communication for Asynchronous Multi-Agent Banditscited by 6
  4. 2023Competing for Shareable Arms in Multi-Player Multi-Armed Banditscited by 6
  5. 2022Collaborative Algorithms for Online Personalized Mean Estimationcited by 5
  6. 2023Collaborative Multi-Agent Heterogeneous Multi-Armed Banditscited by 4
  7. 2024Learning to Control Unknown Strongly Monotone Gamescited by 4
  8. 2021Conservative Contextual Combinatorial Cascading Banditcited by 3
  9. 2024Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationalitycited by 3
  10. 2021A High Performance, Low Complexity Algorithm for Multi-Player Bandits Without Collision Sensing Informationcited by 2
  11. 2022Decentralized Stochastic Multi-Player Multi-Armed Walking Banditscited by 2
  12. 2022The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communicationcited by 1
  13. 2022Multi-Player Bandits Robust to Adversarial Collisionscited by 1
  14. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  15. 2024Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysiscited by 1
  16. 2025Meet Me at the Arm: The Cooperative Multi-Armed Bandits Problem with Shareable Armscited by 1
  17. 2021Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?cited by 0
  18. 2022Robust Multi-Agent Bandits Over Undirected Graphscited by 0
  19. 2022Sequential Decision Problems with Weak Feedbackcited by 0
  20. 2023Constant or logarithmic regret in asynchronous multiplayer banditscited by 0
  21. 2023Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Banditscited by 0
  22. 2023Simple Opinion Dynamics for No-Regret Learningcited by 0
  23. 2023Adversarial Attacks on Cooperative Multi-agent Banditscited by 0
  24. 2024Fair Distributed Cooperative Bandit Learning on Networks for Intelligent Internet of Things Systems (Technical Report)cited by 0
  25. 2024PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creatorscited by 0
  26. 2024Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacitiescited by 0
  27. 2025Competitive Multi-armed Bandit Games for Resource Sharingcited by 0
  28. 2025Competitive Algorithms for Multi-Agent Ski-Rental Problemscited by 0
  29. 2025Decentralized Asynchronous Multi-player Banditscited by 0
  30. 2026Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedbackcited by 0
  31. 2026Regret Analysis of Sleeping Competing Banditscited by 0
  32. 2026A Context Augmented Multi-Play Multi-Armed Bandit Algorithm for Fast Channel Allocation in Opportunistic Spectrum Accesscited by 0
  33. 2026Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocationcited by 0
  34. 2026The Price of Decentralization in Top-K Arm Identificationcited by 0