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.

[1]  M. Runco,et al.  The Standard Definition of Creativity , 2012 .

[2]  Jürgen Schmidhuber,et al.  First Experiments with PowerPlay , 2012, Neural networks : the official journal of the International Neural Network Society.

[3]  Jürgen Schmidhuber,et al.  Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts , 2006, Connect. Sci..

[4]  John E. Laird,et al.  Extending the Soar Cognitive Architecture , 2008, AGI.

[5]  Kristinn R. Thórisson,et al.  Self-Programming: Operationalizing Autonomy , 2009 .

[6]  Jürgen Schmidhuber,et al.  PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem , 2011, Front. Psychol..

[7]  Marcus Hutter,et al.  Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability (Texts in Theoretical Computer Science. An EATCS Series) , 2006 .

[8]  Kristinn R. Thórisson,et al.  Cognitive Architectures and Autonomy: A Comparative Review , 2012, J. Artif. Gen. Intell..

[9]  Pei Wang,et al.  Rigid Flexibility: The Logic of Intelligence , 2006 .

[10]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[11]  Pei Wang,et al.  On the Working Definition of Intelligence , 2003 .

[12]  Kristinn R. Thórisson,et al.  On Attention Mechanisms for AGI Architectures: A Design Proposal , 2012, AGI.

[13]  Peter Dayan,et al.  Technical Note: Q-Learning , 2004, Machine Learning.

[14]  Shane Legg,et al.  A Formal Measure of Machine Intelligence , 2006, ArXiv.

[15]  Shane Legg,et al.  A Collection of Definitions of Intelligence , 2007, AGI.

[16]  Pei Wang Rigid Flexibility: The Logic of Intelligence (Applied Logic Series) , 2006 .

[17]  Jürgen Schmidhuber,et al.  Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010) , 2010, IEEE Transactions on Autonomous Mental Development.