Term of Award
Fall 2017
Degree Name
Master of Science in Mathematics (M.S.)
Document Type and Release Option
Thesis (open access)
Department
Department of Mathematical Sciences
Committee Chair
Stephen Carden
Committee Member 1
Arpita Chatterjee
Committee Member 2
Scott Kersey
Committee Member 3
Ionut Iacob
Abstract
In Markov decision processes an operator exploits known data regarding the environment it inhabits. The information exploited is learned from random exploration of the state-action space. This paper proposes to optimize exploration through the implementation of quasi-random sequences in both discrete and continuous state-action spaces. For the discrete case a permutation is applied to the indices of the action space to avoid repetitive behavior. In the continuous case sequences of low discrepancy, such as Halton sequences, are utilized to disperse the actions more uniformly.
Recommended Citation
Walker, Samuel. "Quasi-Random Action Selection In Markov Decision Processes". November, 2017.
Research Data and Supplementary Material
No
