Title :
A parallel learning cellular automata for combinatorial optimization problems
Author :
Qian, Fei ; Hirata, Hironori
Author_Institution :
Dept. of Comput. Sci., Hiroshima Inst. of Technol., Japan
Abstract :
Reinforcement learning is a class of learning methodologies in which the controller (or agent) adapts based on external feedback from the random environment. We present a theoretic model of stochastic learning cellular automata (SLCA) as a model of reinforcement learning systems. The SLCA is an extended model of traditional cellular automata, defined as a stochastic cellular automaton with its random environment. There are three rule spaces for the SLCA: parallel, sequential and mixture. We especially study the parallel SLCA with a genetic operator and apply it to the combinatorial optimization problems. The computer simulations of graph partition problems show that the convergence of SLCA is better than the parallel mean field algorithm
Keywords :
cellular automata; combinatorial mathematics; genetic algorithms; learning (artificial intelligence); optimisation; parallel algorithms; stochastic automata; SLCA; combinatorial optimization problems; computer simulations; external feedback; genetic operator; graph partition problems; learning methodologies; parallel SLCA; parallel learning cellular automata; parallel mean field algorithm; random environment; reinforcement learning; reinforcement learning systems; rule spaces; stochastic cellular automaton; stochastic learning cellular automata; theoretic model; Automatic control; Computer science; Computer simulation; Feedback; Genetics; Learning automata; Learning systems; Probability distribution; Stochastic processes; Stochastic systems;
Conference_Titel :
Evolutionary Computation, 1996., Proceedings of IEEE International Conference on
Conference_Location :
Nagoya
Print_ISBN :
0-7803-2902-3
DOI :
10.1109/ICEC.1996.542659
