{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86829"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86829","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Reinforcement Learning and Optimal Control in Complex Social Systems","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Yang, Fan; 0000-0002-2501-0745"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Dong, Wen","Computer Science and Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-25T23:23:12Z","date_published":"2025-02-25T23:23:12Z","updated_at":"2026-07-27T19:05:37Z","subjects":["artificial intelligence","computer science"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86829","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dong, Wen","Computer Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Yang, Fan; 0000-0002-2501-0745"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-25T23:23:12Z","2020","2020-08-08 12:20:47"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["artificial intelligence","computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86829"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","Complex social systems are composed of interconnected individuals whose interactions result in group behaviors. Sequential decision making in a real-world complex system has many applications, including road traffic management, epidemic prevention, and information dissemination. However, optimizing the decisions in such real-world complex system is difficult because of the high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decisionmaker. Sequential decision making in complex social systems remain a hot research topic and there are many existing works around it. There are mainly two frameworks of that in complex social systems. One is the single-agent framework which view all the components of the system as a whole and optimize the utility function of the entire system. The other one is the multi-agent framework which view each component as a self-interested agent and each agent optimizes its own utility function. The challenges of solving sequential decision making problems in real-world systems are the huge amount of individuals of different species, the high-dimensional state-action spaces, the complex state transitions, the partial observability, the sophisticated spatial-temporal dependences, the lacking a high-fidelity reward function to reflect the real world need, and the expensiveness in interacting with the environment. We propose to develop reinforcement learning and optimal control algorithms that can effectively and efficiently solve complex social systems decision making problems. For the single-agent framework, we firstly consider a baseline case where the system dynamics and the reward function are known. In this case, we will develop a partially observable discrete event decision process to capture the system dynamics succinctly, and develop a variational inference algorithm with Bethe entropy approximation to tractably solve the optimization problem. We then consider a more realistic scenario with unknown system dynamics and unknown reward functions, which we formulated as an imitation learning problem. To provide better optimization signals and being more robust, we propose to develop a variational kernel learning algorithm to solve this problem. For the multi-agent framework, we consider a real-world scenario where the system dynamics and reward functions are unknown, which we formulated as a multi-agent imitation learning problem. To cope with the exploding dimensionality problem and to maintain scalability, we propose to develop a mean-field kernel algorithm to solve this problem.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Reinforcement Learning and Optimal Control in Complex Social Systems"]}]}],"canonical_facts":{"dc:contributor":["Dong, Wen","Computer Science and Engineering"],"dc:creator":["Yang, Fan; 0000-0002-2501-0745"],"dc:date":["2025-02-25T23:23:12Z","2020","2020-08-08 12:20:47"],"dc:description":["Ph.D.","Complex social systems are composed of interconnected individuals whose interactions result in group behaviors. Sequential decision making in a real-world complex system has many applications, including road traffic management, epidemic prevention, and information dissemination. However, optimizing the decisions in such real-world complex system is difficult because of the high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decisionmaker. Sequential decision making in complex social systems remain a hot research topic and there are many existing works around it. There are mainly two frameworks of that in complex social systems. One is the single-agent framework which view all the components of the system as a whole and optimize the utility function of the entire system. The other one is the multi-agent framework which view each component as a self-interested agent and each agent optimizes its own utility function. The challenges of solving sequential decision making problems in real-world systems are the huge amount of individuals of different species, the high-dimensional state-action spaces, the complex state transitions, the partial observability, the sophisticated spatial-temporal dependences, the lacking a high-fidelity reward function to reflect the real world need, and the expensiveness in interacting with the environment. We propose to develop reinforcement learning and optimal control algorithms that can effectively and efficiently solve complex social systems decision making problems. For the single-agent framework, we firstly consider a baseline case where the system dynamics and the reward function are known. In this case, we will develop a partially observable discrete event decision process to capture the system dynamics succinctly, and develop a variational inference algorithm with Bethe entropy approximation to tractably solve the optimization problem. We then consider a more realistic scenario with unknown system dynamics and unknown reward functions, which we formulated as an imitation learning problem. To provide better optimization signals and being more robust, we propose to develop a variational kernel learning algorithm to solve this problem. For the multi-agent framework, we consider a real-world scenario where the system dynamics and reward functions are unknown, which we formulated as a multi-agent imitation learning problem. To cope with the exploding dimensionality problem and to maintain scalability, we propose to develop a mean-field kernel algorithm to solve this problem.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86829"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["artificial intelligence","computer science"],"dc:title":["Reinforcement Learning and Optimal Control in Complex Social Systems"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:37Z"}