Abstract
An autonomous agent embodied in a humanoid robot, in order to learn from the overwhelming flow of raw and noisy sensory, has to effectively reduce the high spatial-temporal data dimensionality. In this paper we propose a novel method of unsupervised feature extraction and selection with binary space partitioning, followed by a computation of information gain that is interpreted as intrinsic reward, then applied as immediate-reward signal for the reinforcement-learning. The space partitioning is executed by tiny codelets running on a simulated Turing Machine. The features are represented by concept nodes arranged in a hierarchy, in which those of a lower level become the input vectors of a higher level.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Deci, E.L., Ryan, R.M.: Intrinsic motivation and self-determination in human behavior. Plenum Press, New York (1985)
Oudeyer, P.-Y., Kaplan, F.: How can we define intrinsic motivation? In: Proceedings of the Eighth International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems (2008)
Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Transactions of Autonomous Mental Development 2(3), 230–247 (2010)
Skaba, W.: Heuristic Search in Program Space for the AGINAO Cognitive Architecture. In: AGI 2011 Self-Programming Workshop (2001), http://www.iiim.is/wp/wp-content/uploads/2011/05/skaba-agisp-2011.pdf
Skaba, W.: The AGINAO Self-Programming Engine. Submitted to: Journal of Artificial General Intelligence, Special Issue on Self-Programming (2012), http://aginao.com/pub/The_AGINAO_Self-Programming_Engine.pdf
Goertzel, B.: The Hidden Pattern: A Patternist Philosophy of Mind. BrownWalker Press (2006)
Hawkins, J., George, D.: Hierarchical temporal memory (2006), http://www.numenta.com/htm-overview/education/Numenta_HTM_Concepts.pdf
Reiss, S.: Why Extrinsic Motivation Doesn’t Exist. Psychology Today (2011), http://www.psychologytoday.com/blog/who-we-are/201108/why-extrinsic-motivation-doesnt-exist
Cover, T.M., Thomas, J.A.: Elements of Information Theory, p. 20. John Wiley & Sons, Inc. (1991)
Tribus, M.: Thermodynamics and Thermostatics: An Introduction to Energy, Information and States of Matter, with Engineering Applications, Princeton, N.J., Van Nostrand (1961)
Schmidhuber, J., Storck, J., Hochreiter, J.: Reinforcement Driven Information Acquisition In Non-Deterministic Environments. In: ICANN 1995, vol. 2, pp. 159–164. EC2 & CIE, Paris (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Skaba, W. (2012). Binary Space Partitioning as Intrinsic Reward. In: Bach, J., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2012. Lecture Notes in Computer Science(), vol 7716. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35506-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-35506-6_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35505-9
Online ISBN: 978-3-642-35506-6
eBook Packages: Computer ScienceComputer Science (R0)