dc.contributor.author | Fardno, Fatemeh | |
dc.date.accessioned | 2022-09-29 14:04:50 (GMT) | |
dc.date.available | 2023-09-30 04:50:05 (GMT) | |
dc.date.issued | 2022-09-29 | |
dc.date.submitted | 2022-09-27 | |
dc.identifier.uri | http://hdl.handle.net/10012/18841 | |
dc.description.abstract | In this work, we study the application of multi-agent reinforcement learning (RL) in distributed systems. In particular, we consider a setting in which strategic clients compete over a set of heterogeneous servers. Each client receives jobs at a fixed rate. For each job, clients choose a server to run the job. The objective of each client is to minimize its average wait time. We model this setting as a Markov game and theoretically prove that the game becomes in the limit a Markov potential game (MPG). We further propose a novel mean-field reinforcement learning algorithm, combining mean-field Q-learning and fictitious play. Through rigorous experiments, we show that our algorithm outperforms naive deployment of single-agent RL, and in some cases, performs comparably to the Nash Q-learning, while being less complex in terms of memory and computation. We also empirically analyze the convergence of our proposed algorithm to a Nash equilibrium and study its performance in four benchmark examples. | en |
dc.language.iso | en | en |
dc.publisher | University of Waterloo | en |
dc.title | Fictitious Mean-field Reinforcement Learning for Distributed Load Balancing | en |
dc.type | Master Thesis | en |
dc.pending | false | |
uws-etd.degree.department | Electrical and Computer Engineering | en |
uws-etd.degree.discipline | Electrical and Computer Engineering | en |
uws-etd.degree.grantor | University of Waterloo | en |
uws-etd.degree | Master of Applied Science | en |
uws-etd.embargo.terms | 1 year | en |
uws.contributor.advisor | Zahedi, Seyed Majid | |
uws.contributor.affiliation1 | Faculty of Engineering | en |
uws.published.city | Waterloo | en |
uws.published.country | Canada | en |
uws.published.province | Ontario | en |
uws.typeOfResource | Text | en |
uws.peerReviewStatus | Unreviewed | en |
uws.scholarLevel | Graduate | en |