Abstract
Humans and other animals are often touted as examples of systems that possess general intelligence. However, rarely if ever do they achieve high levels of intelligence and autonomy on their own: they are raised by parents and caregivers in a society with peers and seniors, who serve as teachers and examples. Current methods for developing artificial learning systems typically do not account for this. This paper gives a taxonomy of the main methods for raising / educating naturally intelligent systems and provides examples for how these might be applied to artificial systems. The methods are heuristic rewarding, decomposition, simplification, situation selection, teleoperation, demonstration, coaching, explanation, and cooperation. We argue that such tutoring methods that provide assistance in the learning process can be expected to have great benefits when properly applied to certain kinds of artificial systems.
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
Abbeel, P., Coates, A., Ng, A.Y.: Autonomous helicopter aerobatics through apprenticeship learning. The International Journal of Robotics Research 29(13), 1608–1639 (2010)
Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robotics and Autonomous Systems 57(5), 469–483 (2009)
Bengio, Y.: Evolving culture vs local minima. Preprint arXiv:1203.2990 (2012)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of ICML, vol. 26, pp. 41–48 (2009)
Bieger, J., Thórisson, K.R., Garrett, D.: Raising AI: Towards a taxonomy of tutoring methods. Technical Report RUTR-SCS13007, CADIA & SCS, Reykjavik University (April 2014)
Caruana, R.: Multitask learning. Machine Learning 28(1), 41–75 (1997)
Deterding, S., Dixon, D., Khaled, R., Nacke, L.: From game design elements to gamefulness: Defining gamification. In: Proceedings of the 15th International Academic MindTrek Conference, pp. 9–15. ACM (2011)
Goertzel, B.: OpenCogPrime: A cognitive synergy based architecture for artificial general intelligence. In: 8th IEEE International Conference on Cognitive Informatics, ICCI 2009, pp. 60–68 (2009)
Goertzel, B., Bugaj, S.V.: AGI preschool: A framework for evaluating early-stage human-like AGIs. In: Proceedings of AGI 2009, pp. 31–36 (2009)
Guelcehre, C., Bengio, Y.: Knowledge matters: Importance of prior information for optimization. arXiv:1301.4083 (cs, stat) (January 2013)
Holladay, C.L., Quinones, M.A.: Practice variability and transfer of training: The role of self-efficacy generality. Journal of Applied Psychology 88(6), 1094 (2003)
Laud, A., De Jong, G.: The influence of reward on the speed of reinforcement learning: An analysis of shaping. In: ICML, pp. 440–447 (2003)
Louradour, J., Kermorvant, C.: Curriculum learning for handwritten text line recognition. Preprint arXiv:1312.1737 (2013)
Maclin, R., Shavlik, J.W.: Creating advice-taking reinforcement learners. Machine Learning 22(1-3), 251–281 (1996)
Muelling, K., Kober, J., Peters, J.: Learning table tennis with a mixture of motor primitives. In: 2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 411–416. IEEE (2010)
Nivel, E., Thórisson, K.R., Steunebrink, B.R., Dindo, H., Pezzulo, G., Rodriguez, M., Hernandez, C., Ognibene, D., Schmidhuber, J., Sanz, R.: Bounded recursive self-improvement. Preprint arXiv:1312.6764 (2013)
Schapire, R.E.: The boosting approach to machine learning: An overview. In: Nonlinear Estimation and Classification, pp. 149–171. Springer (2003)
Settles, B.: Active learning literature survey. Tech 1648, Madison, Wisconsin (2010)
Skinner, B.F.: The behavior of organisms: An experimental analysis (1938)
Snel, M., Whiteson, S.: Multi-task reinforcement learning: shaping and feature selection. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS, vol. 7188, pp. 237–248. Springer, Heidelberg (2012)
Spitkovsky, V.I., Alshawi, H., Jurafsky, D.: From baby steps to leapfrog: How less is more in unsupervised dependency parsing. In: Human Language Technologies: The 2010 Annual Conference of the NAACL, pp. 751–759 (2010)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction, vol. 116. Cambridge Univ. Press (1998)
Taylor, M.E., Carboni, N., Fachantidis, A., Vlahavas, I., Torrey, L.: Reinforcement learning agents providing advice in complex video games. Connection Science 26(1), 45–63 (2014)
Teague, R.C., Gittelman, S.S., Park, O.C.: A review of the literature on part-task and whole-task training and context dependency. DTIC (1994)
Thomaz, A., Hoffman, G., Breazeal, C.: Real-time interactive reinforcement learning for robots. In: AAAI 2005 Workshop on Human Comprehensible Machine Learning (2005)
Wang, P.: Non-Axiomatic Reasoning System: Exploring the Essence of Intelligence. PhD thesis, Citeseer (1995)
Wickens, C.D., Hutchins, S., Carolan, T., Cumming, J.: Effectiveness of part-task training and increasing-difficulty training strategies a meta-analysis approach. Human Factors 55(2), 461–470 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Bieger, J., Thórisson, K.R., Garrett, D. (2014). Raising AI: Tutoring Matters. In: Goertzel, B., Orseau, L., Snaider, J. (eds) Artificial General Intelligence. AGI 2014. Lecture Notes in Computer Science(), vol 8598. Springer, Cham. https://doi.org/10.1007/978-3-319-09274-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-09274-4_1
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09273-7
Online ISBN: 978-3-319-09274-4
eBook Packages: Computer ScienceComputer Science (R0)