mlsanityData to 14 Oct 2026

DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks

arXiv 2608.11873 ↗First posted 12 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, we extend the Dependent Click Model (DCM) Bandits to a multiplayer information-asymmetric setting, where multiple agents interact with a shared ranked list and may observe multiple clicks per session, introducing new challenges for selection strategies. We study asymmetry in (1) actions and (2) rewards, providing sublinear regret guarantees for three settings where at least one asymmetry is present. Establishing matching information-theoretic lower bounds for these settings is left as an open problem. We further show that for small termination probabilities, the termination ranking need not be known, improving on prior single-agent results. Experiments confirm that our algorithms perform well across asymmetric environments and highlight the critical role of feedback structure, specifically the distinction between full versus first-click feedback, in coordinating exploration and minimizing regret.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

23 of 33 references.

References · 23

  1. 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 77
  2. 2016Delay and Cooperation in Nonstochastic Banditscited by 71
  3. 2014Nonstochastic Multi-Armed Bandits with Graph-Structured Feedbackcited by 61
  4. 2016Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithmscited by 48
  5. 2016Cascading Bandits for Large-Scale Recommendation Problemscited by 45
  6. 2015Combinatorial Cascading Banditscited by 40
  7. 2017Online Clustering of Contextual Cascading Banditscited by 24
  8. 2018Multiplayer bandits without observing collision informationcited by 20
  9. 2016DCM Bandits: Learning to Rank with Multiple Clickscited by 17
  10. 2018Thompson Sampling Algorithms for Cascading Banditscited by 13
  11. 2019Multiplayer Bandit Learning, from Competition to Cooperationcited by 12
  12. 2021Online Learning for Cooperative Multi-Player Multi-Armed Banditscited by 12
11 more
  1. 2019Multi-Player Bandits: The Adversarial Casecited by 11
  2. 2024Federated Combinatorial Multi-Agent Multi-Armed Banditscited by 11
  3. 2020Fatigue-aware Bandits for Dependent Click Modelscited by 10
  4. 2023Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communicationcited by 8
  5. 2025A Survey of Real-World Recommender Systems: Challenges, Constraints, and Industrial Perspectivescited by 7
  6. 2024Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Banditscited by 5
  7. 2024Cascading Reinforcement Learningcited by 4
  8. 2025Multiplayer Information Asymmetric Bandits in Metric Spacescited by 3
  9. 2025Multiplayer Information Asymmetric Contextual Banditscited by 3
  10. 2022Measurement and applications of position bias in a marketplace search enginecited by 2
  11. 2025Cascading Bandits Robust to Adversarial Corruptionscited by 2

Built on by

Not cited yet.