Improved automatic discovery of subgoals for options in hierarchical

• Autores: R. Matthew Kretchmar, Todd Feil, Rohit Bansal
• Localización: Journal of Computer Science and Technology, ISSN-e 1666-6038, Vol. 3, Nº. 2, 2003 (Ejemplar dedicado a: Nineth Issue), págs. 9-14
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Options have been shown to be a key step in extending reinforcement learning beyond low-level reactionary systems to higher-level, planning systems. Most of the options research involves hand-crafted options; there has been only very limited work in the automated discovery of options. We extend early work in automated option discovery with a flexible and robust method.