{"id":{"repo_id":"denver","oai_identifier":"oai:digitalcommons.du.edu:etd-3829"},"canonical_url":"https://search.ndltd.org/etd/denver/oai:digitalcommons.du.edu:etd-3829","repository":{"repo_id":"denver","name":"University of Denver","base_url":"https://digitalcommons.du.edu/do/oai/"},"display":{"title":"Collaborative Federated Learning for Robots in Heterogeneous Environments","abstract":"This research investigates the performance of Federated Averaging (FedAvg) in simulated Federated Learning (FL) scenarios with varying degrees of environmental heterogeneity among robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset of agents encountered an unfamiliar environment. The results demonstrate that while FedAvg exhibits resilience to the introduction of new environmental data, it struggles to ensure both convergence and fairness in heterogeneous settings. Specifically, the original training environment maintains a dominant influence, while agents in novel environments experience inhibited learning. These findings highlight the challenges of applying FedAvg in lifelong learning scenarios with heterogeneous environments and unbalanced non-IID data, revealing a trade-off between maintaining performance in a majority environment and ensuring equitable learning across diverse environments.","abstract_html":"This research investigates the performance of Federated Averaging (FedAvg) in simulated Federated Learning (FL) scenarios with varying degrees of environmental heterogeneity among robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset of agents encountered an unfamiliar environment. The results demonstrate that while FedAvg exhibits resilience to the introduction of new environmental data, it struggles to ensure both convergence and fairness in heterogeneous settings. Specifically, the original training environment maintains a dominant influence, while agents in novel environments experience inhibited learning. These findings highlight the challenges of applying FedAvg in lifelong learning scenarios with heterogeneous environments and unbalanced non-IID data, revealing a trade-off between maintaining performance in a majority environment and ensuring equitable learning across diverse environments.","abstract_has_math":false,"creators":["Schneider, Karlan"],"institution":null,"degree_name":"M.S. in Computer Science","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Stephen Hutt","Mohammad Mahoor","Kerstin Haring","Aaron Kraft"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:55:13Z","subjects":["Collaborative robotics","Deep reinforcement learning","Distributed learning","Federated averaging","Federated learning","Heterogeneous environments","Artificial Intelligence and Robotics","Computer Sciences"],"languages":["English (eng)"],"rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>","Karlan Schneider"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["ETDCRP.2025.156","<a href=\"https://doi.org/10.56902/ETDCRP.2025.156\">https://doi.org/10.56902/ETDCRP.2025.156</a>","https://digitalcommons.du.edu/etd/2594"],"render_values":[{"text":"ETDCRP.2025.156","href":null,"code":true},{"text":"<a href=\"https://doi.org/10.56902/ETDCRP.2025.156\">https://doi.org/10.56902/ETDCRP.2025.156</a>","href":"https://doi.org/10.56902/ETDCRP.2025.156\">https://doi.org/10.56902/ETDCRP.2025.156</a>","code":true},{"text":"https://digitalcommons.du.edu/etd/2594","href":"https://digitalcommons.du.edu/etd/2594","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.56902/ETDCRP.2025.156","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.56902/ETDCRP.2025.156","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.du.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.du.edu%3Aetd-3829","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Stephen Hutt","Mohammad Mahoor","Kerstin Haring","Aaron Kraft"]},{"key":"dc:creator","label":"Author","values":["Schneider, Karlan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.copyright","label":"Dc Date Copyright","values":["2025-06-01T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-06-13T07:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Collaborative robotics","Deep reinforcement learning","Distributed learning","Federated averaging","Federated learning","Heterogeneous environments","Artificial Intelligence and Robotics","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English (eng)"]},{"key":"dc:rights","label":"Dc Rights","values":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"]},{"key":"dc:rights.holder","label":"Dc Rights Holder","values":["Karlan Schneider"]},{"key":"dc:rights.license","label":"Dc Rights License","values":["all_rights_reserved"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["ETDCRP.2025.156","https://doi.org/10.56902/ETDCRP.2025.156","<a href=\"https://doi.org/10.56902/ETDCRP.2025.156\">https://doi.org/10.56902/ETDCRP.2025.156</a>","https://digitalcommons.du.edu/etd/2594"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This research investigates the performance of Federated Averaging (FedAvg) in simulated Federated Learning (FL) scenarios with varying degrees of environmental heterogeneity among robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset of agents encountered an unfamiliar environment. The results demonstrate that while FedAvg exhibits resilience to the introduction of new environmental data, it struggles to ensure both convergence and fairness in heterogeneous settings. Specifically, the original training environment maintains a dominant influence, while agents in novel environments experience inhibited learning. These findings highlight the challenges of applying FedAvg in lifelong learning scenarios with heterogeneous environments and unbalanced non-IID data, revealing a trade-off between maintaining performance in a majority environment and ensuring equitable learning across diverse environments."]},{"key":"dc:description.provenance","label":"Dc Description Provenance","values":["Received from ProQuest"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:format.extent","label":"Dc Format Extent","values":["48 pgs","2.4 MB"]},{"key":"dc:title","label":"Title","values":["Collaborative Federated Learning for Robots in Heterogeneous Environments"]}]}],"canonical_facts":{"dc:contributor":["Stephen Hutt","Mohammad Mahoor","Kerstin Haring","Aaron Kraft"],"dc:creator":["Schneider, Karlan"],"dc:date.copyright":["2025-06-01T07:00:00Z"],"dc:date.created":["2025-06-13T07:00:00Z"],"dc:description.abstract":["This research investigates the performance of Federated Averaging (FedAvg) in simulated Federated Learning (FL) scenarios with varying degrees of environmental heterogeneity among robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset of agents encountered an unfamiliar environment. The results demonstrate that while FedAvg exhibits resilience to the introduction of new environmental data, it struggles to ensure both convergence and fairness in heterogeneous settings. Specifically, the original training environment maintains a dominant influence, while agents in novel environments experience inhibited learning. These findings highlight the challenges of applying FedAvg in lifelong learning scenarios with heterogeneous environments and unbalanced non-IID data, revealing a trade-off between maintaining performance in a majority environment and ensuring equitable learning across diverse environments."],"dc:description.provenance":["Received from ProQuest"],"dc:format":["application/pdf"],"dc:format.extent":["48 pgs","2.4 MB"],"dc:identifier":["ETDCRP.2025.156","https://doi.org/10.56902/ETDCRP.2025.156","<a href=\"https://doi.org/10.56902/ETDCRP.2025.156\">https://doi.org/10.56902/ETDCRP.2025.156</a>","https://digitalcommons.du.edu/etd/2594"],"dc:language":["English (eng)"],"dc:rights":["<p>Copyright is held by the author. User is responsible for all copyright compliance.</p>"],"dc:rights.holder":["Karlan Schneider"],"dc:rights.license":["all_rights_reserved"],"dc:subject":["Collaborative robotics","Deep reinforcement learning","Distributed learning","Federated averaging","Federated learning","Heterogeneous environments","Artificial Intelligence and Robotics","Computer Sciences"],"dc:title":["Collaborative Federated Learning for Robots in Heterogeneous Environments"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["M.S. in Computer Science"]},"updated_at":"2026-11-19T07:55:13Z"}