A New Approach to the Design of Reinforcement Schemes for Learning Automata: Stochastic Estimator Learning Algorithms

Authors:
G. I. Papadimitriou
Affiliations:
-
Venue:
IEEE Transactions on Knowledge and Data Engineering
Year:
1994

Citing 1
Cited 11

Nonstationary models of learning automata routing in data communication networks

IEEE Transactions on Systems, Man and Cybernetics

Absorbing stochastic estimator learning automata for S-model stationary environments

Information Sciences—Informatics and Computer Science: An International Journal
Efficient fast learning automata

Information Sciences—Informatics and Computer Science: An International Journal
Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments

Pattern Recognition
A new high rate adaptive wireless data dissemination scheme

Computer Communications
Group-Linking Method: A Unified Benchmark for Machine Learning with Recurrent Neural Network

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Performance optimization of an adaptive wireless push system in environments with locality of demand

Computer Communications
An adaptive call admission algorithm for cellular networks

Computers and Electrical Engineering
A new traffic engineering routing algorithm for MPLS networks

WiCOM'09 Proceedings of the 5th International Conference on Wireless communications, networking and mobile computing
On utilizing stochastic learning weak estimators for training and classification of patterns with non-stationary distributions

KI'05 Proceedings of the 28th annual German conference on Advances in Artificial Intelligence
An efficient adaptive bus arbitration scheme for scalable shared-medium ATM switch

Computer Communications
Performance evaluation of acoustic underwater data broadcasting exploiting the bandwidth-distance relationship

Mobile Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new class of learning automata is introduced. The new automata use a stochastic estimator and are able to operate in nonstationary environments with high accuracy and a high adaptation rate. According to the stochastic estimator scheme, the estimates of the mean rewards of actions are computed stochastically. So, they are not strictly dependent on the environmental responses. The dependence between the stochastic estimates and the deterministic estimator's contents is more relaxed when the latter are old and probably invalid. In this way, actions that have not been selected recently have the opportunity to be estimated as "optimal", to increase their choice probability, and, consequently, to be selected. Thus, the estimator is always recently updated and consequently is able to be adapted to environmental changes. The performance of the Stochastic Estimator Learning Automaton (SELA) is superior to the previous well-known S-model ergodic schemes. Furthermore, it is proved that SELA is absolutely expedient in every stationary S-model random environment.