Term of Award
Spring 2024
Degree Name
Master of Science in Mathematics (M.S.)
Document Type and Release Option
Thesis (open access)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department
Department of Mathematical Sciences
Committee Chair
Stephen Carden
Committee Member 1
Ionut Iacob
Committee Member 2
Zheni Utic
Abstract
Reinforcement learning (RL) is a subfield of machine learning concerned with agents learning to behave optimally by interacting with an environment. One of the most important topics in RL is how the agent should explore, that is, how to choose actions in order to rate their impact on long-term reward. For example, a simple baseline strategy might be uniformly random action selection. This thesis investigates the heuristic idea that agents will learn faster if they explore by factoring the environment’s state into their decision and intentionally choose actions which are as different as possible from what they have previously observed. Experiments are run to discover whether this algorithm is computationally reasonable, and whether the agent learns significantly faster compared to baseline exploration strategies.
OCLC Number
1430435189
Catalog Permalink
https://galileo-georgiasouthern.primo.exlibrisgroup.com/permalink/01GALI_GASOUTH/1r4bu70/alma9916564849002950
Recommended Citation
Svishchev, Aleksandr, "Reinforcement Learning: Applying Low Discrepancy Action Selection to Deep Deterministic Policy Gradient" (2024). Electronic Theses and Dissertations. 2707.
https://digitalcommons.georgiasouthern.edu/etd/2707
Research Data and Supplementary Material
No