{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/127124"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/127124","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Multi-agent reinforcement learning: A mean-field perspective","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_has_math":false,"creators":["Zaman, Muhammad Aneeq Uz"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":["Başar, Tamer","Dullerud, Geir","Jiang, Nan","Srikant, Rayadurgam"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-07-24","date_published":"2024-07-24","updated_at":"2026-07-22T22:25:03Z","subjects":["Multi-agent Reinforcement Learning","Mean-field Game Theory","Policy Gradient Methods","Actor-critic Methods","Cooperative-competitive Games"],"languages":["en","eng"],"rights":["Copyright 2024 Muhammad Aneeq Uz Zaman"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/127124","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Başar, Tamer","Dullerud, Geir","Jiang, Nan","Srikant, Rayadurgam"]},{"key":"dc:creator","label":"Author","values":["Zaman, Muhammad Aneeq Uz"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-07-24","2024-12"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Multi-agent Reinforcement Learning","Mean-field Game Theory","Policy Gradient Methods","Actor-critic Methods","Cooperative-competitive Games"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Muhammad Aneeq Uz Zaman"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/127124"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Muhammad Aneeq Uz Zaman, accepted the attached license on 2024-07-10 at 22:30.","The student, Muhammad Aneeq Uz Zaman, submitted this Dissertation for approval on 2024-07-10 at 22:38.","This Dissertation was approved for publication on 2024-07-24 at 09:00.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21061 on 2025-03-28 at 14:24:40","Recent advancements in Reinforcement Learning (RL) have enabled significant progress in solving complex decision-making problems across various domains such as robotics, autonomous driving, and strategy games. However, many real-world scenarios involve multiple agents cooperating and competing with each other to achieve common goals, necessitating the development of Multi-Agent RL (MARL) algorithms. MARL not only addresses the challenges posed by interactions among agents but also enables robust learning in dynamic environments. Mean-Field Games (MFGs) offer a promising framework to tackle scalability issues in RL for multiple decision-making agents by considering the limiting case where the number of agents approaches infinity. Originating from seminal works, MFGs have seen extensive research, extensions, and applications in diverse fields. The thesis focuses on extending RL techniques for purely competitive games (Chapters 2, 3 and 6), Cooperative-Competitive (CC) games (Chapter 4) and the robust N -agent cooperative control problem (Chapter 5). Within purely competitive games Chapter 2 deals with a consensus problem where the agents are split into multiple populations. Although the thesis primarily deals with the Linear Quadratic (LQ) framework (which has applications in finance and engineering), we dedicate Chapter 3 to a general large population Markov game where we relax the assumption of access to a population (mean-field) simulator prevalent in literature. Chapter 4 is regarding a CC game where the agents are divided into multiple teams where these is intra-team cooperation and inter-team competition. Chapter 5 pertains to a purely cooperative control problem where the agents’ dynamics and cost functions can be manipulated by an adversary. This chapter takes the min-max approach by characterizing optimal policies in the presence of the worst adversarial manipulation. Chapter 6 investigates the effects of entropy regularization on cost functions of competitive agents and how it results in exploratory noise in the control policies of the agents. In each of these chapters we start with a literature review highlighting existing approaches and gaps in research. Then we characterize the various equilibria corresponding to each of the problems, followed by RL algorithms to compute these equilibria (in a data driven manner) along with finite sample guarantees and numerical validations."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Multi-agent reinforcement learning: A mean-field perspective"]}]}],"canonical_facts":{"dc:contributor":["Başar, Tamer","Dullerud, Geir","Jiang, Nan","Srikant, Rayadurgam"],"dc:creator":["Zaman, Muhammad Aneeq Uz"],"dc:date":["2024-07-24","2024-12"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Muhammad Aneeq Uz Zaman, accepted the attached license on 2024-07-10 at 22:30.","The student, Muhammad Aneeq Uz Zaman, submitted this Dissertation for approval on 2024-07-10 at 22:38.","This Dissertation was approved for publication on 2024-07-24 at 09:00.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21061 on 2025-03-28 at 14:24:40","Recent advancements in Reinforcement Learning (RL) have enabled significant progress in solving complex decision-making problems across various domains such as robotics, autonomous driving, and strategy games. However, many real-world scenarios involve multiple agents cooperating and competing with each other to achieve common goals, necessitating the development of Multi-Agent RL (MARL) algorithms. MARL not only addresses the challenges posed by interactions among agents but also enables robust learning in dynamic environments. Mean-Field Games (MFGs) offer a promising framework to tackle scalability issues in RL for multiple decision-making agents by considering the limiting case where the number of agents approaches infinity. Originating from seminal works, MFGs have seen extensive research, extensions, and applications in diverse fields. The thesis focuses on extending RL techniques for purely competitive games (Chapters 2, 3 and 6), Cooperative-Competitive (CC) games (Chapter 4) and the robust N -agent cooperative control problem (Chapter 5). Within purely competitive games Chapter 2 deals with a consensus problem where the agents are split into multiple populations. Although the thesis primarily deals with the Linear Quadratic (LQ) framework (which has applications in finance and engineering), we dedicate Chapter 3 to a general large population Markov game where we relax the assumption of access to a population (mean-field) simulator prevalent in literature. Chapter 4 is regarding a CC game where the agents are divided into multiple teams where these is intra-team cooperation and inter-team competition. Chapter 5 pertains to a purely cooperative control problem where the agents’ dynamics and cost functions can be manipulated by an adversary. This chapter takes the min-max approach by characterizing optimal policies in the presence of the worst adversarial manipulation. Chapter 6 investigates the effects of entropy regularization on cost functions of competitive agents and how it results in exploratory noise in the control policies of the agents. In each of these chapters we start with a literature review highlighting existing approaches and gaps in research. Then we characterize the various equilibria corresponding to each of the problems, followed by RL algorithms to compute these equilibria (in a data driven manner) along with finite sample guarantees and numerical validations."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/127124"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Muhammad Aneeq Uz Zaman"],"dc:subject":["Multi-agent Reinforcement Learning","Mean-field Game Theory","Policy Gradient Methods","Actor-critic Methods","Cooperative-competitive Games"],"dc:title":["Multi-agent reinforcement learning: A mean-field perspective"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:03Z"}