{"id":{"repo_id":"fsu-retro","oai_identifier":"oai:diginole.lib.fsu.edu:fsu_927986"},"canonical_url":"https://search.dev.ndltd.org/etd/fsu-retro/oai:diginole.lib.fsu.edu:fsu_927986","repository":{"repo_id":"fsu-retro","name":"Florida State University","base_url":"https://repository.lib.fsu.edu/oai2"},"display":{"title":"Joint Vehicle Dispatching and Redeployment for Emergency Medical Services with Multi-Critic Reinforcement Learning","abstract":"With regard to Emergency Medical Services (EMS), the response time and consistency that they can provide care to in need patients is of the upmost importance. The key aspects of achieving this efficiency lies in how the EMS vehicles are dispatched to a patient from the currently available fleet and how they are then redistributed to best cover the area of care. This problem can be formulated as both a Markov-Decision Process and as a Multi-Agent Markov Game in which we can find some optimal policy to best assist those in needs. Previous works have approached this problem in both the combined sense (considering dispatching and redeployment as a single problem) or as two separate systems to optimize. Deep Reinforcement Learning (DRL) has been growing in popularity over the past half decade, and applications of these advances are still underutilized for this problem. While methods within the DRL family have been applied to this problem, they typically only consider the dispatching or redistribution sides independently, there has been a growing field of interest in applying one DRL policy to multiple tasks. Our approach is centered around improving the redeployment side of the problem but we will also be exploring the benefits of using a single policy to approach two aspects of a conjoined problem to improve the response time and consistency of these vital services.","abstract_html":"With regard to Emergency Medical Services (EMS), the response time and consistency that they can provide care to in need patients is of the upmost importance. The key aspects of achieving this efficiency lies in how the EMS vehicles are dispatched to a patient from the currently available fleet and how they are then redistributed to best cover the area of care. This problem can be formulated as both a Markov-Decision Process and as a Multi-Agent Markov Game in which we can find some optimal policy to best assist those in needs. Previous works have approached this problem in both the combined sense (considering dispatching and redeployment as a single problem) or as two separate systems to optimize. Deep Reinforcement Learning (DRL) has been growing in popularity over the past half decade, and applications of these advances are still underutilized for this problem. While methods within the DRL family have been applied to this problem, they typically only consider the dispatching or redistribution sides independently, there has been a growing field of interest in applying one DRL policy to multiple tasks. Our approach is centered around improving the redeployment side of the problem but we will also be exploring the benefits of using a single policy to approach two aspects of a conjoined problem to improve the response time and consistency of these vital services.","abstract_has_math":false,"creators":[],"institution":"Florida State University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Mendelsohn, David (author)","Wang, Guang (professor directing thesis)","Li, Ang (committee member)","Wu, Te-Yen (committee member)","Florida State University (degree granting institution)","College of Arts and Sciences (degree granting college)","Department of Computer Science (degree granting department)"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T19:35:18Z","subjects":["Computer science"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["fsu:927986","iid: Mendelsohn_fsu_0071N_18745"],"render_values":[{"text":"fsu:927986","href":null,"code":true},{"text":"iid: Mendelsohn_fsu_0071N_18745","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Mendelsohn, David (author)","Wang, Guang (professor directing thesis)","Li, Ang (committee member)","Wu, Te-Yen (committee member)","Florida State University (degree granting institution)","College of Arts and Sciences (degree granting college)","Department of Computer Science (degree granting department)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Florida State University"]},{"key":"dc:type","label":"Dc Type","values":["Text","master thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["fsu:927986","iid: Mendelsohn_fsu_0071N_18745"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["With regard to Emergency Medical Services (EMS), the response time and consistency that they can provide care to in need patients is of the upmost importance. The key aspects of achieving this efficiency lies in how the EMS vehicles are dispatched to a patient from the currently available fleet and how they are then redistributed to best cover the area of care. This problem can be formulated as both a Markov-Decision Process and as a Multi-Agent Markov Game in which we can find some optimal policy to best assist those in needs. Previous works have approached this problem in both the combined sense (considering dispatching and redeployment as a single problem) or as two separate systems to optimize. Deep Reinforcement Learning (DRL) has been growing in popularity over the past half decade, and applications of these advances are still underutilized for this problem. While methods within the DRL family have been applied to this problem, they typically only consider the dispatching or redistribution sides independently, there has been a growing field of interest in applying one DRL policy to multiple tasks. Our approach is centered around improving the redeployment side of the problem but we will also be exploring the benefits of using a single policy to approach two aspects of a conjoined problem to improve the response time and consistency of these vital services.","A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science.","April 5, 2024.","Includes bibliographical references.","Guang Wang, Professor Directing Thesis; Ang Li, Committee Member; Te-Yen Wu, Committee Member."]},{"key":"dc:format","label":"Dc Format","values":["computer","online resource","1 online resource (58 pages)","application/pdf"]},{"key":"dc:title","label":"Title","values":["Joint Vehicle Dispatching and Redeployment for Emergency Medical Services with Multi-Critic Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor":["Mendelsohn, David (author)","Wang, Guang (professor directing thesis)","Li, Ang (committee member)","Wu, Te-Yen (committee member)","Florida State University (degree granting institution)","College of Arts and Sciences (degree granting college)","Department of Computer Science (degree granting department)"],"dc:date":["2024"],"dc:description":["With regard to Emergency Medical Services (EMS), the response time and consistency that they can provide care to in need patients is of the upmost importance. The key aspects of achieving this efficiency lies in how the EMS vehicles are dispatched to a patient from the currently available fleet and how they are then redistributed to best cover the area of care. This problem can be formulated as both a Markov-Decision Process and as a Multi-Agent Markov Game in which we can find some optimal policy to best assist those in needs. Previous works have approached this problem in both the combined sense (considering dispatching and redeployment as a single problem) or as two separate systems to optimize. Deep Reinforcement Learning (DRL) has been growing in popularity over the past half decade, and applications of these advances are still underutilized for this problem. While methods within the DRL family have been applied to this problem, they typically only consider the dispatching or redistribution sides independently, there has been a growing field of interest in applying one DRL policy to multiple tasks. Our approach is centered around improving the redeployment side of the problem but we will also be exploring the benefits of using a single policy to approach two aspects of a conjoined problem to improve the response time and consistency of these vital services.","A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science.","April 5, 2024.","Includes bibliographical references.","Guang Wang, Professor Directing Thesis; Ang Li, Committee Member; Te-Yen Wu, Committee Member."],"dc:format":["computer","online resource","1 online resource (58 pages)","application/pdf"],"dc:identifier":["fsu:927986","iid: Mendelsohn_fsu_0071N_18745"],"dc:language":["English"],"dc:publisher":["Florida State University"],"dc:subject":["Computer science"],"dc:title":["Joint Vehicle Dispatching and Redeployment for Emergency Medical Services with Multi-Critic Reinforcement Learning"],"dc:type":["Text","master thesis"]},"updated_at":"2026-07-27T19:35:18Z"}