Stepwise Evolutionary Learning using Deep Learned Guidance Functions

Autor:	Colin G. Johnson
Přispěvatelé:	Bramer, Max, Petridis, Miltos
Jazyk:	angličtina
Rok vydání:	2019
Předmět:	Fitness function Artificial neural network QA76.87 business.industry Computer science Evolutionary algorithm Evolutionary learning Cube (algebra) Artificial intelligence business Baseline (configuration management) Random forest Test (assessment)
Zdroj:	Lecture Notes in Computer Science ISBN: 9783030348847 SGAI Conf.
ISSN:	0302-9743
Popis:	This paper explores how Learned Guidance Functions (LGFs)— a pre-training method used to smooth search landscapes—can be used as a fitness function for evolutionary algorithms. A new form of LGF is introduced, based on deep neural network learning, and it is shown how this can be used as a fitness function. This is applied to a test problem: unscrambling the Rubik’s Cube. Comparisons are made with a previous LGF approach based on random forests, and with a baseline approach based on traditional error-based fitness.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f1105b96ad8a377af5d740446a14426 https://kar.kent.ac.uk/78198/1/BCS_SGAI_2019.pdf Zobrazit plný text záznamu