Applying Continuous Action Reinforcement Learning Automata(CARLA) to Global Training of Hidden Markov Models

Authors:
Jahanshah Kabudian;Mohammad Reza Meybodi;Mohammad Mehdi Homayounpour
Affiliations:
-;-;-
Venue:
ITCC '04 Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC'04) Volume 2 - Volume 2
Year:
2004

Citing 0
Cited 4

An Efficient Dynamic Algorithm for Maintaining All-Pairs Shortest Paths in Stochastic Networks

IEEE Transactions on Computers
Modeling a student-classroom interaction in a tutorial-like system using learning automata

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Modeling a domain in a tutorial-like system using learning automata

Acta Cybernetica
Modeling a teacher in a tutorial-like system using learning automata

Transactions on Computational Collective Intelligence VIII

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this research, we have employed global search andglobal optimization techniques based on SimulatedAnnealing (SA) and Continuous Action ReinforcementLearning Automata (CARLA) for global training ofHidden Markov Models. The main goal of this paper iscomparing CARLA method to other continuous globaloptimization methods like SA. Experimental resultsshow that the CARLA outperforms SA. This is due to thefact that CARLA is a continuous global optimizationmethod with memory and SA is a memoryless one.