Reinforcement Learning endowed with safe veto policies to learn the control of Linked-Multicomponent Robotic Systems

Borja Fernández-Gauna, Manuel Graña, José Manuel López-Guede, Ismael Etxeberria Agiriano, Igor Ansoategui. Reinforcement Learning endowed with safe veto policies to learn the control of Linked-Multicomponent Robotic Systems. Inf. Sci., 317:25-47, 2015. [doi]

Abstract

Abstract is missing.