The main objective of Transfer Learning is to reuse knowledge acquired in a previous learned task, in order to enhance the learning procedure in a new and more complex task. Transfer learning comprises a suitable solution for speeding up the learning procedure in Reinforcement Learning tasks. This work proposes a novel method for transferring models to Reinforcement Learning agents. The models ...

1DDS, MSc, PhD, Graduate Student, Department of Operative Dentistry, Bauru Dental School, University of São Paulo, Brazil. 2DDS, MSc, Graduate Student, Department of Operative Dentistry, Bauru Dental School, University of São Paulo, Brazil. 3Undergraduate Student of Bauru Dental School, University of São Paulo, Brazil. 4Associate Professor of Operative Dentistry, Dean of Bauru Dental School, Un...

We present two comparison principles for viscosity suband supersolutions of Monge-Ampère-type equations associated to a family of vector fields. In particular, we obtain the uniqueness of a viscosity solution to the Dirichlet problem for the equation of prescribed horizontal Gauss curvature in a Carnot group.

Faculdade de Medicina, Universidade Federal de Minas Gerais – UFMG Belo Horizonte (MG), Brasil. (2) Departamento de Engenharia de Estruturas da Escola de Engenharia, Universidade Federal de Minas Gerais – UFMG Belo Horizonte (MG), Brasil. (3) Departamento de Estatística do Instituto de Ciências Exatas da Universidade Federal de Minas Gerais – UFMG Belo Horizonte (MG), Brasil. (4) Departamento d...