Observatorio de I+D+i UPM

Memorias de investigación
Capítulo de libro:
Bounded Seed-AGI
Año:2014
Áreas de investigación
  • Inteligencia artificial
Datos
Descripción
Four principal features of autonomous control systems are left both unaddressed and unaddressable by present-day engineering methodologies: (1) The ability to operate effectively in environments that are only partially known at design time; (2) A level of generality that allows a system to re-assess and re- define the fulfillment of its mission in light of unexpected constraints or other un- foreseen changes in the environment; (3) The ability to operate effectively in en- vironments of significant complexity; and (4) The ability to degrade gracefully? how it can continue striving to achieve its main goals when resources become scarce, or in light of other expected or unexpected constraining factors that im- pede its progress. We describe new methodological and engineering principles for addressing these shortcomings, that we have used to design a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as expe- rience accumulates. The work provides an architectural blueprint for construct- ing systems with high levels of operational autonomy in underspecified circum- stances, starting from only a small amount of designer-specified code?a seed. Using value-driven dynamic priority scheduling to control the parallel execution of a vast number of lines of reasoning, the system accumulates increasingly useful models of its experience, resulting in recursive self-improvement that can be au- tonomously sustained after the machine leaves the lab, within the boundaries im- posed by its designers. A prototype system named AERA has been implemented and demonstrated to learn a complex real-world task?real-time multimodal dia- logue with humans?by on-line observation. Our work presents solutions to sev- eral challenges that must be solved for achieving artificial general intelligence.
Internacional
Si
DOI
10.1007/978-3-319-09274-4_9
Edición del Libro
Editorial del Libro
Springer International Publishing
ISBN
978-3-319-09273-7
Serie
Lecture Notes in Computer Science
Título del Libro
Artificial General Intelligence
Desde página
85
Hasta página
96
Esta actividad pertenece a memorias de investigación
Participantes
  • Autor: Eric Nivel (Icelandic Institute for Intelligent Machines, IIIM)
  • Autor: Kristinn R. Thorisson (Icelandic Institute for Intelligent Machines, IIIM)
  • Autor: Bas R. Steunebrink (The Swiss AI Lab IDSIA, USI)
  • Autor: Haris Dindo (Universita degli studi di Palermo, DINFO)
  • Autor: Giovanni Pezzulo (Consiglio Nazionale delle Ricerche, ISTC)
  • Autor: Manuel Rodriguez Hernandez (UPM)
  • Autor: Carlos Hernández Corbato (UPM)
  • Autor: Dimitri Ognibene (Consiglio Nazionale delle Ricerche, ISTC)
  • Autor: Jürgen Schmidhuber (The Swiss AI Lab IDSIA, USI)
  • Autor: Ricardo Sanz Bravo (UPM)
  • Autor: Helgi P. Helgason (Reykjavik University, CADIA)
  • Autor: Antonio Chella (Universita degli studi di Palermo, DINFO)
Grupos de investigación, Departamentos, Centros e Institutos de I+D+i relacionados
  • Creador: Grupo de Investigación: Laboratorio de Sistemas Autónomos
  • Centro o Instituto I+D+i: Centro de Automática y Robótica (CAR). Centro Mixto UPM-CSIC
  • Departamento: Ingeniería Química Industrial y del Medio Ambiente
  • Departamento: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial
S2i 2021 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)