Uma arquitetura híbrida aplicada em problemas de aprendizagem por reforço / A hybrid architecture to address reinforcement learning problems

AUTOR(ES)
FONTE

IBICT - Instituto Brasileiro de Informação em Ciência e Tecnologia

DATA DE PUBLICAÇÃO

07/02/2012

RESUMO

With the evergrowing use of cognitive systems in various applications, it has been created a high expectation and a large demand for machines more and more autonomous, intelligent and creative in real world problem solving. In several cases, the challenges ask for high adaptive and learning capability. This work deals with the concepts of reinforcement learning, and reasons on the main solution approaches and problem variations. Subsequently, it builds a hybrid proposal incorporating other machine learning ideas, so that the proposal is validated with simulated experiments. The experiments allow to point out the main advantages of the proposed methodology, founded on its capability to handle continuous space environments, and also to learn an optimal policy while following an exploratory policy. The proposed architecture is hybrid in the sense that it is based on a multi-layer perceptron neural network coupled with a function approximator called wire-fitting. The referred architecture is coordinated by a dynamic and adaptive algorithm which merges concepts from dynamic programming, Monte Carlo analysis, temporal difference learning, and eligibility. The proposed model is used to solve optimal control problems, by means of reinforcement learning, in scenarios endowed with continuous variables and nonlinear development. Two different instances of control problems, well discussed in the pertinent literature, are presented and tested with the same architecture.

ASSUNTO(S)

inteligência artificial aprendizado do computador teoria dos autômatos robótica robôs móveis artificial intelligence machine learning theory of automata robotics mobile robots

Documentos Relacionados