Efficient Decentralized Multi-Agent Learning in Asymmetric Bipartite Queuing Systems
Name
Weng-wweng-SM-EECS-2023-thesis.pdf
Description
Thesis PDF
Size
1.33 MB
Format
Adobe PDF
Checksum (MD5)
ae0f61529bd1b83c1f2afffc80fc0359
Author(s)
Weng, Wentao
Advisor(s)
Freund, Daniel
Lykouris, Thodoris
Date Issued
February 2023
Publisher
Massachusetts Institute of Technology
Abstract
We study decentralized multi-agent learning in bipartite queuing systems, a standard model for service systems. In particular, 𝑁 agents request service from 𝐾 servers in a fully decentralized way, i.e, by running the same algorithm without communication. Previous decentralized algorithms are restricted to symmetric systems, have performance that is degrading exponentially in the number of servers, require communication through shared randomness and unique agent identities, and are computationally demanding. In contrast, we provide a simple learning algorithm that, when run decentrally by each agent, leads the queuing system to have efficient performance in general asymmetric bipartite queuing systems while also having additional robustness properties. Along the way, we provide the first provably efficient UCB-based algorithm for the centralized case of the problem.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link