{"id":{"repo_id":"texas","oai_identifier":"oai:repositories.lib.utexas.edu:2152/134070"},"canonical_url":"https://search.dev.ndltd.org/etd/texas/oai:repositories.lib.utexas.edu:2152/134070","repository":{"repo_id":"texas","name":"University of Texas","base_url":"https://repositories.lib.utexas.edu/server/oai/request"},"display":{"title":"Deep reinforcement learning in RoboCup Keepaway","abstract":"The central theme in multi-agent reinforcement learning often involves the coordination of agents to accomplish a common task. However, in complex environ- ments, the agent action space scales exponentially with the number of agents. As a result of this complexity, the coordination graph formalism allows the construction of a joint policy by decomposing the joint action values into an aggregation of local action-value functions. This approach is concerned with maximizing the joint opti- mal action of coordinating agents. In this thesis, we demonstrate and analyze how coordinated reinforcement learning can be used to learn a multi-agent policy on the RoboCup Keepaway domain, a sub-task of the RoboCup 2D soccer domain. This the- sis contributes to the enhanced implementation of the RoboCup Keepaway in Python and the Analysis of the Deep Coordination Graph and Deep Implicit Coordination Graph Algorithms.","abstract_html":"The central theme in multi-agent reinforcement learning often involves the coordination of agents to accomplish a common task. However, in complex environ- ments, the agent action space scales exponentially with the number of agents. As a result of this complexity, the coordination graph formalism allows the construction of a joint policy by decomposing the joint action values into an aggregation of local action-value functions. This approach is concerned with maximizing the joint opti- mal action of coordinating agents. In this thesis, we demonstrate and analyze how coordinated reinforcement learning can be used to learn a multi-agent policy on the RoboCup Keepaway domain, a sub-task of the RoboCup 2D soccer domain. This the- sis contributes to the enhanced implementation of the RoboCup Keepaway in Python and the Analysis of the Deep Coordination Graph and Deep Implicit Coordination Graph Algorithms.","abstract_has_math":false,"creators":["Adekanmbi, Abayomi"],"institution":"The University of Texas at Austin","degree_name":"Master of Science in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Stone, Peter, 1971-"],"committee_chairs":[],"committee_members":["Plaxton, C Greg"],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-24T05:00:58Z","subjects":["Reinforcement learning"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.26153/tsw/61397"],"render_values":[{"text":"https://doi.org/10.26153/tsw/61397","href":"https://doi.org/10.26153/tsw/61397","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2152/134070","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Stone, Peter, 1971-"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Plaxton, C Greg"]},{"key":"dc:creator","label":"Author","values":["Adekanmbi, Abayomi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-08-29T01:54:09Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["The University of Texas at Austin"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Reinforcement learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2152/134070","https://doi.org/10.26153/tsw/61397"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The central theme in multi-agent reinforcement learning often involves the coordination of agents to accomplish a common task. However, in complex environ- ments, the agent action space scales exponentially with the number of agents. As a result of this complexity, the coordination graph formalism allows the construction of a joint policy by decomposing the joint action values into an aggregation of local action-value functions. This approach is concerned with maximizing the joint opti- mal action of coordinating agents. In this thesis, we demonstrate and analyze how coordinated reinforcement learning can be used to learn a multi-agent policy on the RoboCup Keepaway domain, a sub-task of the RoboCup 2D soccer domain. This the- sis contributes to the enhanced implementation of the RoboCup Keepaway in Python and the Analysis of the Deep Coordination Graph and Deep Implicit Coordination Graph Algorithms."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep reinforcement learning in RoboCup Keepaway"]}]}],"canonical_facts":{"dc:contributor.advisor":["Stone, Peter, 1971-"],"dc:contributor.committeemember":["Plaxton, C Greg"],"dc:creator":["Adekanmbi, Abayomi"],"dc:date.accessioned":["2025-08-29T01:54:09Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["The central theme in multi-agent reinforcement learning often involves the coordination of agents to accomplish a common task. However, in complex environ- ments, the agent action space scales exponentially with the number of agents. As a result of this complexity, the coordination graph formalism allows the construction of a joint policy by decomposing the joint action values into an aggregation of local action-value functions. This approach is concerned with maximizing the joint opti- mal action of coordinating agents. In this thesis, we demonstrate and analyze how coordinated reinforcement learning can be used to learn a multi-agent policy on the RoboCup Keepaway domain, a sub-task of the RoboCup 2D soccer domain. This the- sis contributes to the enhanced implementation of the RoboCup Keepaway in Python and the Analysis of the Deep Coordination Graph and Deep Implicit Coordination Graph Algorithms."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/2152/134070","https://doi.org/10.26153/tsw/61397"],"dc:language.iso":["English"],"dc:subject":["Reinforcement learning"],"dc:title":["Deep reinforcement learning in RoboCup Keepaway"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science in Computer Science"],"thesis:institution_name":["The University of Texas at Austin"]},"updated_at":"2026-07-24T05:00:58Z"}