Publication Date

2025

Document Type

Thesis

Committee Members

Xiaodong Zhang, Ph.D. (Advisor); Trevor Bihl, Ph.D. (Committee Member); Weisong Wang, Ph.D. (Committee Member)

Degree Name

Master of Science in Electrical Engineering (MSEE)

Abstract

This thesis investigates the integration of relational observations with the reinforcement learning (RL) framework for improved generalization capability. A hide-and-seek simulation environment is designed in Unity for proof-of-concept demonstration. Two observation representations—relational (analogical) and standard positional—are designed to evaluate agent learning and generalization capabilities. Agents are trained using the Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC) algorithms in a random-room environment and tested in both the random-room environment and a novel environment with greater spatial complexity and path obstructions. Comparative studies indicate that relational representation of objects in the adversarial environment could potentially improve the generalization capability of RL agents to novel and complex environments. Cross-testing results also suggest that relational observations may enhance agents’ effectiveness in pursuit and evasion tasks in adversarial environments.

Page Count

58

Department or Program

Department of Electrical Engineering

Year Degree Awarded

2025

ORCID ID

0009-0009-4653-9806


Share

COinS