Quantum Inspired Reinforcement Learning in Changing Environment

Pegah Fakhari; Karthikeyan Rajagopal; S. N. Balakrishnan; J. R. Busemeyer

doi:10.1142/S1793005713400073

Quantum Inspired Reinforcement Learning in Changing Environment

Pegah Fakhari
, Karthikeyan Rajagopal
, S. N. Balakrishnan
, J. R. Busemeyer

Missouri University of Science and Technology

Research output: Contribution to journal › Article › peer-review

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. © 2013 World Scientific Publishing Company.

Original language	American English
Journal	New Mathematics and Natural Computation
DOIs	https://doi.org/10.1142/S1793005713400073
State	Published - Jan 1 2013

Disciplines

Aerospace Engineering
Mechanical Engineering

Access to Document

10.1142/S1793005713400073License: Unspecified

https://doi.org/10.1142/S1793005713400073

Cite this

@article{a31bf1bbaf7b483fa61dfedb308866fd,

title = "Quantum Inspired Reinforcement Learning in Changing Environment",

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. {\textcopyright} 2013 World Scientific Publishing Company.",

author = "Pegah Fakhari and Karthikeyan Rajagopal and Balakrishnan, \{S. N.\} and Busemeyer, \{J. R.\}",

year = "2013",

month = jan,

day = "1",

doi = "10.1142/S1793005713400073",

language = "American English",

journal = "New Mathematics and Natural Computation",

issn = "1793-7027",

}

TY - JOUR

T1 - Quantum Inspired Reinforcement Learning in Changing Environment

AU - Fakhari, Pegah

AU - Rajagopal, Karthikeyan

AU - Balakrishnan, S. N.

AU - Busemeyer, J. R.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - 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. © 2013 World Scientific Publishing Company.

AB - 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. © 2013 World Scientific Publishing Company.

UR - https://scholarsmine.mst.edu/mec_aereng_facwork/1187

UR - https://doi.org/10.1142/S1793005713400073

U2 - 10.1142/S1793005713400073

DO - 10.1142/S1793005713400073

M3 - Article

SN - 1793-7027

JO - New Mathematics and Natural Computation

JF - New Mathematics and Natural Computation

ER -

Quantum Inspired Reinforcement Learning in Changing Environment

Abstract

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this