Varieties of Cellular Learning Automata: An Overview

Abstract

Cellular learning automaton (CLA), as one of the artificial intelligence techniques in reinforcement learning, is a combination of cellular automata (CA) and learning automata (LA). Since CLA has both the computational power of cellular automata and the learning ability of learning automata, it is a useful technique for modeling, controlling, and solving many real problems in the unknown, distributed, and decentralized environments. In this chapter, first, we provide an overview of CA and LA, then we focus on the recent variants of CLA models such as asynchronous CLA, open synchronous CLA, irregular CLA, dynamic irregular CLA, heterogeneous dynamic irregular CLA, wavefront CLA, and associative CLA. Finally, we present brief descriptions of the recent applications of the different models of CLA for solving real problems.