{"id":{"repo_id":"texas","oai_identifier":"oai:repositories.lib.utexas.edu:2152/134508"},"canonical_url":"https://search.dev.ndltd.org/etd/texas/oai:repositories.lib.utexas.edu:2152/134508","repository":{"repo_id":"texas","name":"University of Texas","base_url":"https://repositories.lib.utexas.edu/server/oai/request"},"display":{"title":"LightMARL : smart swarm coordination in urban spaces","abstract":"Multi-Agent Reinforcement Learning (MARL) systems generally require substantial computational resources and high-bandwidth communication, which restricts their deployment to centralized cloud infrastructures. This thesis introduces LightMARL, an optimization framework that facilitates effective multi-agent coordination on resource-constrained edge devices while ensuring coordination quality and real-time performance. LightMARL tackles three primary challenges: computational efficiency, communication overhead, and scalability. To improve computation, the framework utilizes neural network quantization, structured pruning, and knowledge distillation tailored for multi-agent policy optimization (MAPPO). These methods decrease model size and computational demands while maintaining essential coordination behaviors. To enhance communication efficiency, vector quantization combined with delta compression, attention-driven selective information sharing, and predictive protocols minimize bandwidth usage and latency. The framework is structured as a modular Python system incorporating C++ components, supporting deployment on Nvidia Jetson platforms. Experimental validation in simulated environments, including drone swarms, vehicle platooning, and sensor networks, demonstrates the framework’s effectiveness. This study illustrates that complex multi-agent coordination is possible on edge devices, enabling new applications in autonomous functionality.","abstract_html":"Multi-Agent Reinforcement Learning (MARL) systems generally require substantial computational resources and high-bandwidth communication, which restricts their deployment to centralized cloud infrastructures. This thesis introduces LightMARL, an optimization framework that facilitates effective multi-agent coordination on resource-constrained edge devices while ensuring coordination quality and real-time performance. LightMARL tackles three primary challenges: computational efficiency, communication overhead, and scalability. To improve computation, the framework utilizes neural network quantization, structured pruning, and knowledge distillation tailored for multi-agent policy optimization (MAPPO). These methods decrease model size and computational demands while maintaining essential coordination behaviors. To enhance communication efficiency, vector quantization combined with delta compression, attention-driven selective information sharing, and predictive protocols minimize bandwidth usage and latency. The framework is structured as a modular Python system incorporating C++ components, supporting deployment on Nvidia Jetson platforms. Experimental validation in simulated environments, including drone swarms, vehicle platooning, and sensor networks, demonstrates the framework’s effectiveness. This study illustrates that complex multi-agent coordination is possible on edge devices, enabling new applications in autonomous functionality.","abstract_has_math":false,"creators":["Murali, Abhejay"],"institution":"The University of Texas at Austin","degree_name":"Master of Science in Computer Sciences","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Jiao, Junfeng","Zhu, Yuke"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-08","date_published":"2025-08","updated_at":"2026-07-24T05:00:58Z","subjects":["Edge computing","Multi-Agent Reinforcement Learning","Drone swarms"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.26153/tsw/61831"],"render_values":[{"text":"https://doi.org/10.26153/tsw/61831","href":"https://doi.org/10.26153/tsw/61831","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2152/134508","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Jiao, Junfeng","Zhu, Yuke"]},{"key":"dc:creator","label":"Author","values":["Murali, Abhejay"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-11T00:08:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-08"]},{"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 Sciences"]},{"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":["Edge computing","Multi-Agent Reinforcement Learning","Drone swarms"]}]},{"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/2152/134508","https://doi.org/10.26153/tsw/61831"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Multi-Agent Reinforcement Learning (MARL) systems generally require substantial computational resources and high-bandwidth communication, which restricts their deployment to centralized cloud infrastructures. This thesis introduces LightMARL, an optimization framework that facilitates effective multi-agent coordination on resource-constrained edge devices while ensuring coordination quality and real-time performance. LightMARL tackles three primary challenges: computational efficiency, communication overhead, and scalability. To improve computation, the framework utilizes neural network quantization, structured pruning, and knowledge distillation tailored for multi-agent policy optimization (MAPPO). These methods decrease model size and computational demands while maintaining essential coordination behaviors. To enhance communication efficiency, vector quantization combined with delta compression, attention-driven selective information sharing, and predictive protocols minimize bandwidth usage and latency. The framework is structured as a modular Python system incorporating C++ components, supporting deployment on Nvidia Jetson platforms. Experimental validation in simulated environments, including drone swarms, vehicle platooning, and sensor networks, demonstrates the framework’s effectiveness. This study illustrates that complex multi-agent coordination is possible on edge devices, enabling new applications in autonomous functionality."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["LightMARL : smart swarm coordination in urban spaces"]}]}],"canonical_facts":{"dc:contributor.advisor":["Jiao, Junfeng","Zhu, Yuke"],"dc:creator":["Murali, Abhejay"],"dc:date.accessioned":["2025-10-11T00:08:06Z"],"dc:date.issued":["2025-08"],"dc:description.abstract":["Multi-Agent Reinforcement Learning (MARL) systems generally require substantial computational resources and high-bandwidth communication, which restricts their deployment to centralized cloud infrastructures. This thesis introduces LightMARL, an optimization framework that facilitates effective multi-agent coordination on resource-constrained edge devices while ensuring coordination quality and real-time performance. LightMARL tackles three primary challenges: computational efficiency, communication overhead, and scalability. To improve computation, the framework utilizes neural network quantization, structured pruning, and knowledge distillation tailored for multi-agent policy optimization (MAPPO). These methods decrease model size and computational demands while maintaining essential coordination behaviors. To enhance communication efficiency, vector quantization combined with delta compression, attention-driven selective information sharing, and predictive protocols minimize bandwidth usage and latency. The framework is structured as a modular Python system incorporating C++ components, supporting deployment on Nvidia Jetson platforms. Experimental validation in simulated environments, including drone swarms, vehicle platooning, and sensor networks, demonstrates the framework’s effectiveness. This study illustrates that complex multi-agent coordination is possible on edge devices, enabling new applications in autonomous functionality."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/2152/134508","https://doi.org/10.26153/tsw/61831"],"dc:language.iso":["English"],"dc:subject":["Edge computing","Multi-Agent Reinforcement Learning","Drone swarms"],"dc:title":["LightMARL : smart swarm coordination in urban spaces"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science in Computer Sciences"],"thesis:institution_name":["The University of Texas at Austin"]},"updated_at":"2026-07-24T05:00:58Z"}