Date of Award
Spring 6-13-2025
Document Type
Masters Thesis
Degree Name
M.S. in Computer Science
Organizational Unit
Daniel Felix Ritchie School of Engineering and Computer Science, Computer Science
First Advisor
Stephen Hutt
Second Advisor
Mohammad Mahoor
Third Advisor
Kerstin Haring
Fourth Advisor
Aaron Kraft
Copyright Statement / License for Reuse
All Rights Reserved.
Keywords
Collaborative robotics, Deep reinforcement learning, Distributed learning, Federated averaging, Federated learning, 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.
Copyright Date
6-2025
Publication Statement
Copyright is held by the author. User is responsible for all copyright compliance.
Rights Holder
Karlan Schneider
Provenance
Received from ProQuest
File Format
application/pdf
Language
English (eng)
Extent
48 pgs
File Size
2.4 MB
Recommended Citation
Schneider, Karlan, "Collaborative Federated Learning for Robots in Heterogeneous Environments" (2025). Electronic Theses and Dissertations. 2594.
https://digitalcommons.du.edu/etd/2594