ABSOLUTELY EXPEDIENT LEARNING ALGORITHMS FOR STOCHASTIC AUTOMATA

被引：0

作者：

LAKSHMIVARAHAN, S ^{[1
]}

THATHACHAR, MA ^{[1
]}

机构：

[1] INDIAN INST SCI, DEPT ELECT ENGN, BANGALORE, INDIA

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1973年 / SMC3卷 / 03期

关键词：

LEARNING ALGORITHMS - STOCHASTIC AUTOMATA;

D O I：

10.1109/TSMC.1973.4309220

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A general but simple condition of symmetry of the nonlinear functions figuring in the reinforcement scheme is shown to be necessary and sufficient for absolute expediency (monotonic decrease of the expectation of the average penalty in all stationary random media). Various schemes are simulated and the results are compared. An adaptive updating of the parameters in the scheme to obtain faster convergence is proposed.

引用

页码：281 / 286

页数：6

共 50 条

[1] ABSOLUTELY EXPEDIENT ALGORITHMS FOR LEARNING NASH EQUILIBRIA
PHANSALKAR, VV
SASTRY, PS
THATHACHAR, MAL
PROCEEDINGS OF THE INDIAN ACADEMY OF SCIENCES-MATHEMATICAL SCIENCES, 1994, 104 (01): : 279 - 294
[2] Absolutely expedient algorithms for learning Nash equilibria
Phansalkar, V.V.
Sastry, P.S.
Thathachar, M.A.L.
Proceedings of the Indian Academy of Sciences: Mathematical Sciences, 1994, 104 (01):
[3] A note on absolutely expedient learning rules
Oyarzun, Carlos
JOURNAL OF ECONOMIC THEORY, 2014, 153 : 213 - 223
[4] INVESTIGATION OF CONVERGENCE OF ALGORITHMS FOR FUNCTIONING OF LEARNING STOCHASTIC AUTOMATA
POZNYAK, AS
AUTOMATION AND REMOTE CONTROL, 1975, 36 (01) : 77 - 91
[5] Sampling algorithms for stochastic graphs: A learning automata approach
Rezvanian, Alireza
Meybodi, Mohammad Reza
KNOWLEDGE-BASED SYSTEMS, 2017, 127 : 126 - 144
[6] AUTOMATA WITH EXPEDIENT BEHAVIOR WHICH CONTROL STOCHASTIC OBJECT
GREBENJUK, EA
AVTOMATIKA I VYCHISLITELNAYA TEKHNIKA, 1980, (01): : 47 - 54
[7] Learning automata-accelerated greedy algorithms for stochastic submodular maximization
Di, Chong
Li, Fangqi
Xu, Pengyao
Guo, Ying
Chen, Chao
Shu, Minglei
KNOWLEDGE-BASED SYSTEMS, 2023, 282
[8] Absolutely expedient imitative behavior
Morales, AJ
INTERNATIONAL JOURNAL OF GAME THEORY, 2003, 31 (04) : 475 - 492
[9] Absolutely expedient imitative behavior
Antonio J. Morales
International Journal of Game Theory, 2003, 31 : 475 - 492
[10] A NEW APPROACH TO THE DESIGN OF REINFORCEMENT SCHEMES FOR LEARNING AUTOMATA - STOCHASTIC ESTIMATOR LEARNING ALGORITHMS
PAPADIMITRIOU, GI
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1994, 6 (04) : 649 - 654

← 1 2 3 4 5 →