Multi-Agent Lipschitz Bandits
Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen

TL;DR
This paper introduces a communication-free multi-agent Lipschitz bandit algorithm that achieves near-optimal regret bounds by combining a novel coordination protocol with independent single-agent bandit solutions, applicable to continuous action spaces.
Contribution
It presents the first framework with provable guarantees for decentralized multi-agent Lipschitz bandits, including a novel maxima-directed search for coordination and decoupling into single-agent problems.
Findings
Achieves near-optimal regret of O(T^{(d+1)/(d+2)})
Provides a coordination protocol with T-independent costs
Extends to general collision models
Abstract
We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward. Our objective is to design a communication-free policy that maximizes collective reward, with coordination costs that are independent of the time horizon . We propose a modular protocol that first solves the multi-agent coordination problem -- identifying and seating players on distinct high-value regions via a novel maxima-directed search -- and then decouples the problem into independent single-player Lipschitz bandits. We establish a near-optimal regret bound of plus a -independent coordination cost, matching the single-player rate. To our knowledge, this is the first framework providing such guarantees, and it extends to general distance-threshold collision models.
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 · Game Theory and Applications · Reinforcement Learning in Robotics
