Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies
Shaojie Tang, Yaqin Zhou

TL;DR
This paper extends classical multi-armed bandit problems to networked combinatorial settings, analyzing strategies with side observations and rewards across four scenarios, and proposing zero-regret policies validated by simulations.
Contribution
It introduces a comprehensive framework for networked combinatorial bandits with side information, providing zero-regret policies for four new problem scenarios.
Findings
Zero regret policies are achievable in all four scenarios.
Extensive simulations confirm the effectiveness of the proposed strategies.
The framework models real-world social network feedback mechanisms.
Abstract
In this paper, we investigate a largely extended version of classical MAB problem, called networked combinatorial bandit problems. In particular, we consider the setting of a decision maker over a networked bandits as follows: each time a combinatorial strategy, e.g., a group of arms, is chosen, and the decision maker receives a reward resulting from her strategy and also receives a side bonus resulting from that strategy for each arm's neighbor. This is motivated by many real applications such as on-line social networks where friends can provide their feedback on shared content, therefore if we promote a product to a user, we can also collect feedback from her friends on that product. To this end, we consider two types of side bonus in this study: side observation and side reward. Upon the number of arms pulled at each time slot, we study two cases: single-play and combinatorial-play.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Auction Theory and Applications · Cognitive Radio Networks and Spectrum Sensing
