Resource-boundedness must be carefully considered when designing and implementing artificial general intelligence (AGI) algorithms and architectures that have to deal with the real world. But not only must resources be represented explicitly throughout its design, an agent must also take into account their usage and the associated costs during reasoning and acting. Moreover, the agent must be intrinsically motivated to become progressively better at utilizing resources. This drive then naturally leads to effectiveness, efficiency, and curiosity. We propose a practical operational framework that explicitly takes into account resource constraints: activities are organized to maximally utilize an agent’s bounded resources as well as the availability of a teacher, and to drive the agent to become progressively better at utilizing its resources. We show how an existing AGI architecture called AERA can function inside this framework. In short, the capability of AERA to perform self-compilation can be used to motivate the system to not only accumulate knowledge and skills faster, but also to achieve goals using less resources, becoming progressively more effective and efficient.
This research was funded by the EU projects HumanObs (FP7-ICT-231453), IM-CLeVeR (FP7-ICT-231722), and Nascence (FP7-ICT-317662), and by SNF grant #200020-138219.
This is a preview of subscription content, access via your institution.
Unable to display preview. Download preview PDF.
Helgason, H.P., Nivel, E., Thórisson, K.R.: On attention mechanisms for AGI architectures: A design proposal. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 89–98. Springer, Heidelberg (2012)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004) (On J. Schmidhuber’s SNF grant 20-61847)
Laird, J.E.: Extending the soar cognitive architecture. In: Proceedings of the First Conference on Artificial General Intelligence. Springer, Memphis (2008)
Legg, S., Hutter, M.: A collection of definitions of intelligence. In: Proceedings of the First Annual Artificial General Intelligence Workshop (2006)
Legg, S., Hutter, M.: A formal measure of machine intelligence. In: Proceedings of the Annual Machine Learning Conference of Belgium and The Netherlands, Benelearn (2006)
Nivel, E., Thórisson, K.R.: Self-programming: Operationalizing autonomy. In: Proceedings of the Second Conference on Artificial General Intelligence (2009)
Runco, M.A., Jaeger, G.J.: The standard definition of creativity. Creativity Research Journal 24, 92–96 (2012)
Schmidhuber, J.: Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts. Connection Science 18(2), 173–187 (2006)
Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Transactions on Autonomous Mental Development 2(3), 230–247 (2010)
Schmidhuber, J.: PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem. In: Frontiers in Cognitive Science (in press, 2013) (Preprint (2011): arXiv:1112.5309 [cs.AI])
Srivastava, R.K., Steunebrink, B.R., Schmidhuber, J.: First experiments with PowerPlay. Neural Networks (2013)
Thórisson, K.R., Helgasson, H.P.: Cognitive architectures and autonomy: A comparative review. Journal of Artificial General Intelligence 3(2) (2012)
Wang, P.: On the working definition of intelligence. Tech. rep. (1995)
Wang, P.: Rigid Flexibility: The Logic of Intelligence. Springer (2006)
Watkins, C., Dayan, P.: Q-learning. Machine Learning 8(3/4), 279–292 (1992)
Editors and Affiliations
Rights and permissions
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Steunebrink, B.R., Koutník, J., Thórisson, K.R., Nivel, E., Schmidhuber, J. (2013). Resource-Bounded Machines are Motivated to be Effective, Efficient, and Curious. In: Kühnberger, KU., Rudolph, S., Wang, P. (eds) Artificial General Intelligence. AGI 2013. Lecture Notes in Computer Science(), vol 7999. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39521-5_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39520-8
Online ISBN: 978-3-642-39521-5
eBook Packages: Computer ScienceComputer Science (R0)