Keywords

Reinforcement Learning, Catastrophic Forgetting, Proximal Policy Optimization, Experience Replay Buffers

Abstract

Catastrophic Forgetting continues to be a prevalent issue for any neural-based approach to learning. Without better understanding and solutions to solving catastrophic forgetting, learning performance and efficacy in autonomous agents, particularly deep learning-based agents will become drastically hindered. Current literature contains approaches to reduce the effects of catastrophic forgetting via task decomposition, rehearsal, and layered learning. However, critical agent knowledge is still susceptible to being driven out of these agents with state-of-the-art techniques. This research explores how prioritized experience replay buffers impact an agent’s ability to retain critical knowledge and combat catastrophic forgetting, using the logic problem: Leading Ones * Trailing Zeros. Additionally, this work introduces two new prioritization schemes that are compared against baseline non-buffered approaches. From the experiments conducted, this research accomplished optimality for one type of prioritized buffer, beating the baseline approaches. Furthermore, the results show a tradeoff between the inclusion of experience replay buffers and how much rehearsal is most beneficial to aiding an agent’s performance.

Completion Date

2024

Semester

Summer

Committee Chair

Mondesire, Sean

Degree

Master of Science (M.S.)

College

College of Engineering and Computer Science

Department

Computer Science

Format

application/pdf

URL

https://stars.library.ucf.edu/cgi/viewcontent.cgi?article=1327&context=etd2023

Language

English

Rights

In copyright

Release Date

August 2025

Length of Campus-only Access

1 year

Access Status

Masters Thesis (Campus-only Access)

Campus Location

Orlando (Main) Campus

Accessibility Status

Meets minimum standards for ETDs/HUTs

Download

Restricted to the UCF community until August 2025; it will then be open access.

Share

COinS