QUANTUM INSPIRED REINFORCEMENT LEARNING IN CHANGING ENVIRONMENT

被引：10

作者：

Fakhari, Pegah ^{[1
]}

Rajagopal, Karthikeyan ^{[2
]}

Balakrishnan, S. N. ^{[2
]}

Busemeyer, J. R. ^{[1
]}

机构：

[1] Indiana Univ, Dept Psychol & Brain Sci, Bloomington, IN 47405 USA

[2] Univ Mississippi, Dept Mech Aerosp & Engn Mech, Rolla, MO 38677 USA

来源：

NEW MATHEMATICS AND NATURAL COMPUTATION | 2013年 / 9卷 / 03期

基金：

美国国家科学基金会;

关键词：

Reinforcement learning; quantum RL; prey and predator dilemma;

D O I：

10.1142/S1793005713400073

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

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.

引用

页码：273 / 294

页数：22

共 10 条

[1] Bertsekas D. P., 1996, NEURO DYNAMIC PROGRA
[2] Busemeyer J. R., 2012, QUANTUM MODELS COGNI, DOI [10.1017/CBO9780511997716, DOI 10.1017/CBO9780511997716]
[3] Quantum reinforcement learning
Dong, Daoyi
Chen, Chunlin
Li, Hanxiong
Tarn, Tzyh-Jong
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2008, 38 (05): : 1207 - 1220
[4] Dong DY, 2005, LECT NOTES COMPUT SC, V3611, P686
[5] Even-Dar E, 2003, J MACH LEARN RES, V5, P1
[6] Grover L. K., 1996, Proceedings of the Twenty-Eighth Annual ACM Symposium on the Theory of Computing, P212, DOI 10.1145/237814.237866
[7] Quantum mechanics helps in searching for a needle in a haystack
Grover, LK
[J]. PHYSICAL REVIEW LETTERS, 1997, 79 (02) : 325 - 328
[8] Shor P. W., 1994, Proceedings. 35th Annual Symposium on Foundations of Computer Science (Cat. No.94CH35717), P124, DOI 10.1109/SFCS.1994.365700
[9] Sutton R. S., 1988, Machine Learning, V3, P9, DOI 10.1007/BF00115009
[10] Sutton R. S., 1998, INTRO REINFORCEMENT, V2

← 1 →