Resource-Bounded Machines are Motivated to be Effective, Efficient, and Curious
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.
Unable to display preview. Download preview PDF.
- 2.Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004) (On J. Schmidhuber’s SNF grant 20-61847) Google Scholar
- 3.Laird, J.E.: Extending the soar cognitive architecture. In: Proceedings of the First Conference on Artificial General Intelligence. Springer, Memphis (2008)Google Scholar
- 4.Legg, S., Hutter, M.: A collection of definitions of intelligence. In: Proceedings of the First Annual Artificial General Intelligence Workshop (2006)Google Scholar
- 5.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)Google Scholar
- 6.Nivel, E., Thórisson, K.R.: Self-programming: Operationalizing autonomy. In: Proceedings of the Second Conference on Artificial General Intelligence (2009)Google Scholar
- 10.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]) Google Scholar
- 11.Srivastava, R.K., Steunebrink, B.R., Schmidhuber, J.: First experiments with PowerPlay. Neural Networks (2013)Google Scholar
- 12.Thórisson, K.R., Helgasson, H.P.: Cognitive architectures and autonomy: A comparative review. Journal of Artificial General Intelligence 3(2) (2012)Google Scholar
- 13.Wang, P.: On the working definition of intelligence. Tech. rep. (1995)Google Scholar
- 14.Wang, P.: Rigid Flexibility: The Logic of Intelligence. Springer (2006)Google Scholar