QUANTUM INSPIRED REINFORCEMENT LEARNING IN CHANGING ENVIRONMENT

Pegah Fakhari (), Karthikeyan Rajagopal, S. N. Balakrishnan and J. R. Busemeyer
Additional contact information
Pegah Fakhari: Department of Psychological and Brain Sciences, Indiana University Bloomington, United States
Karthikeyan Rajagopal: Department of Mechanical, Aerospace and Engineering Mechanics, University of Missouri-Rolla, United States
S. N. Balakrishnan: Department of Mechanical, Aerospace and Engineering Mechanics, University of Missouri-Rolla, United States
J. R. Busemeyer: Department of Psychological and Brain Sciences, Indiana University Bloomington, United States

New Mathematics and Natural Computation (NMNC), 2013, vol. 09, issue 03, 273-294

Abstract: Inspired by quantum theory and reinforcement learning, a new framework of learning in unknown probabilistic environment is proposed. Several simulated experiments are given; the results demonstrate the robustness of the new algorithm for some complex problems. Also we generalized the Grover algorithm to improve the rate of converging to an optimal path. In other words, the new generalized algorithm helps to increase the probability of selecting good actions with better weights' adjustments.

Keywords: Reinforcement learning; quantum RL; prey and predator dilemma (search for similar items in EconPapers)
Date: 2013
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S1793005713400073
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:nmncxx:v:09:y:2013:i:03:n:s1793005713400073

Ordering information: This journal article can be ordered from

DOI: 10.1142/S1793005713400073

Access Statistics for this article

New Mathematics and Natural Computation (NMNC) is currently edited by Paul P Wang

More articles in New Mathematics and Natural Computation (NMNC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().