Reinforcement Learning using Gaussian Processes for Discretely Controlled Continuous Processes

• Autores: de Paula, Mariano; Martinez, Ernesto Carlos
• Año de publicación: 2013
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: Hybrid Systems; Stochastic Systems; Optimization; Reinforcement Learning; Gaussian Processes
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

In many application domains such as autonomous avionics, power electronics and process systems engineering there exist discretely controlled continuous processes (DCCPs) which constitute a special subclass of hybrid dynamical systems. We introduce a novel simulation-based approach for DDCPs optimization under uncertainty using Rein-forcement Learning with Gaussian Process models to learn the transitions dynamics descriptive of mode execution and an optimal switching policy for mode selection. Each mode implements a parameterized feedback control law until a stopping condition trig-gers. To deal with the size/dimension of the state space and a continuum of control mode parameters, Bayesian active learning is proposed using a utility function that trades off information content with policy improvement. Throughput maximization in a buffer tank subject to an uncertain schedule of sev-eral inflow discharges is used as case study address-ing supply chain control in manufacturing systems
Fil: de Paula, Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológio - CONICET - Santa Fe. Instituto de Desarrollo y Diseño (i); Argentina
Fil: Martinez, Ernesto Carlos. Consejo Nacional de Invest.cientif.y Tecnicas. Centro Cientifico Tecnol.conicet - Santa Fe. Instituto de Desarrollo y Dise?o (i);