Heuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems

Nenhuma Miniatura disponível
Citações na Scopus
8
Tipo de produção
Artigo
Data
2014
Autores
Ferreira L.A.
Costa Ribeiro C.H.
Da Costa Bianchi R.A.
Orientador
Periódico
Applied Intelligence
Título da Revista
ISSN da Revista
Título de Volume
Citação
FERREIRA, LEONARDO ANJOLETTO; COSTA RIBEIRO, CARLOS HENRIQUE; DA COSTA BIANCHI, REINALDO AUGUSTO. Heuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems. Applied Intelligence (Boston), v. 1, p. 1-12, 2014.
Texto completo (DOI)
Palavras-chave
Resumo
This article presents two new algorithms for finding the optimal solution of a Multi-agent Multi-objective Reinforcement Learning problem. Both algorithms make use of the concepts of modularization and acceleration by a heuristic function applied in standard Reinforcement Learning algorithms to simplify and speed up the learning process of an agent that learns in a multi-agent multi-objective environment. In order to verify performance of the proposed algorithms, we considered a predator-prey environment in which the learning agent plays the role of prey that must escape the pursuing predator while reaching for food in a fixed location. The results show that combining modularization and acceleration using a heuristics function indeed produced simplification and speeding up of the learning process in a complex problem when comparing with algorithms that do not make use of acceleration or modularization techniques, such as Q-Learning and Minimax-Q. © 2014 Springer Science+Business Media New York.

Coleções