A key goal in designing an artificial intelligence capable of performing complex tasks is a mechanism that allows it to efficiently choose appropriate and relevant actions in a variety of situations and contexts. Nowhere is this more obvious than in the case of building a general intelligence, where the contextual choice and application of actions must be done in the presence of large numbers of alternatives, both subtly and obviously distinct from each other. We present a framework for action selection based on the concurrent activity of multiple forward and inverse models. A key characteristic of the proposed system is the use of simulation to choose an action: the system continuously simulates the external states of the world (proximal and distal) by internally emulating the activity of its sensors, adopting the same decision process as if it were actually operating in the world, and basing subsequent choice of action on the outcome of such simulations. The work is part of our larger effort to create new observation-based machine learning techniques. We describe our approach, an early implementation, and an evaluation in a classical AI problem-solving domain: the Sokoban puzzle.

Dindo, H., LA TONA, G., Nivel, E., Pezzulo, G., Chella, A., & Thórisson, K. (2013). Simulation and Anticipation as Tools for Coordinating with the Future. In A. Chella, R. Pirrone, S. Sorbello, & Jòhannsodottir (a cura di), Biologically Inspired Cognitive Architectures 2012 (pp. 117-125). springer Berlin Heidelberg [10.1007/978-3-642-34274-5_24].

Simulation and Anticipation as Tools for Coordinating with the Future

DINDO, Haris;LA TONA, Giuseppe;CHELLA, Antonio;
2013

Abstract

A key goal in designing an artificial intelligence capable of performing complex tasks is a mechanism that allows it to efficiently choose appropriate and relevant actions in a variety of situations and contexts. Nowhere is this more obvious than in the case of building a general intelligence, where the contextual choice and application of actions must be done in the presence of large numbers of alternatives, both subtly and obviously distinct from each other. We present a framework for action selection based on the concurrent activity of multiple forward and inverse models. A key characteristic of the proposed system is the use of simulation to choose an action: the system continuously simulates the external states of the world (proximal and distal) by internally emulating the activity of its sensors, adopting the same decision process as if it were actually operating in the world, and basing subsequent choice of action on the outcome of such simulations. The work is part of our larger effort to create new observation-based machine learning techniques. We describe our approach, an early implementation, and an evaluation in a classical AI problem-solving domain: the Sokoban puzzle.
Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni
Dindo, H., LA TONA, G., Nivel, E., Pezzulo, G., Chella, A., & Thórisson, K. (2013). Simulation and Anticipation as Tools for Coordinating with the Future. In A. Chella, R. Pirrone, S. Sorbello, & Jòhannsodottir (a cura di), Biologically Inspired Cognitive Architectures 2012 (pp. 117-125). springer Berlin Heidelberg [10.1007/978-3-642-34274-5_24].
File in questo prodotto:
File Dimensione Formato  
Doc-27-05-13 16-49.pdf

non disponibili

Descrizione: Copertina
Dimensione 4.63 MB
Formato Adobe PDF
4.63 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Doc-27-05-13 16-52.pdf

non disponibili

Descrizione: Table of Contents
Dimensione 6.37 MB
Formato Adobe PDF
6.37 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Dindo et al. - 2013 - Simulation and Anticipation as Tools for Coordinating with the Future.pdf

non disponibili

Descrizione: Articolo principale
Dimensione 1.02 MB
Formato Adobe PDF
1.02 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10447/78424
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 2
social impact