Abstract
The ability to predict the unfolding of future events is an important feature of any situated AGI system. The most widely used approach is to create a model of the world, initialize it with the desired start state and use it to simulate possible future scenarios. In this paper we propose an alternative approach where there is no explicit model building involved. The agent memorizes its personal autobiography in an unprocessed narrative form. When a prediction is needed, the agent aligns story-lines from the autobiography with the current story, extends them into the future, then interprets them in the terms of the current events. We describe the implementation of this approach in the Xapagy cognitive architecture and present some experiments illustrating its operation.
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
Anderson, J., Bothell, D., Byrne, M., Douglass, S., Lebiere, C., Qin, Y.: An integrated theory of the mind. Psychological Review 111(4), 1036 (2004)
Anderson, J., Lebiere, C.: The atomic components of thought. Lawrence Erlbaum (1998)
Bölöni, L.: A cookbook of translating English to Xapi. arXiv:1304.0715 (2013)
Forbus, K., Riesbeck, C., Birnbaum, L., Livingston, K., Sharma, A., Ureel, L.: Integrating natural language, knowledge representation and reasoning, and analogical processing to learn by reading. In: Proc. of AAAI, pp. 1542–1547 (2007)
Goertzel, B., Ke, S., Lian, R., O’Neill, J., Sadeghi, K., Wang, D., Watkins, O., Yu, G.: The CogPrime architecture for embodied artificial general intelligence. In: IEEE Symposium on Computational Intelligence for Human-like Intelligence (CIHLI 2013), pp. 60–67. IEEE (2013)
Hanurav, T.: Optimum utilization of auxiliary information: π ps sampling of two units from a stratum. Journal of the Royal Statistical Society. Series B (Methodological), 374–391 (1967)
Lehman, J., Laird, J., Rosenbloom, P., et al.: A gentle introduction to Soar, an architecture for human cognition, vol. 4, pp. 211–253. MIT Press (1998)
Mills, C.W.: The sociological imagination. Oxford University Press (1959)
Mueller, E.: Understanding script-based stories using commonsense reasoning. Cognitive Systems Research 5(4), 307–340 (2004)
Parsons, T.: The social system. Psychology Press (1951)
Rosenbloom, P.S.: Rethinking cognitive architecture via graphical models. Cognitive Systems Research 12(2), 198–209 (2011)
Schank, R., Abelson, R., et al.: Scripts, plans, goals and understanding: An inquiry into human knowledge structures, vol. 2. Lawrence Erlbaum Associates Nueva Jersey (1977)
Schubert, L., Hwang, C.: Episodic Logic meets Little Red Riding Hood: A comprehensive, natural representation for language understanding. Natural Language Processing and Knowledge Representation: Language for Knowledge and Knowledge for Language, 111–174 (2000)
Vijayan, K.: An exact π ps sampling scheme-generalization of a method of hanurav. Journal of the Royal Statistical Society. Series B (Methodological), 556–566 (1968)
Winston, P.H.: The strong story hypothesis and the directed perception hypothesis. In: Langley, P. (ed.) Technical Report FS-11-01, Papers from the AAAI Fall Symposium, pp. 345–352. AAAI Press, Menlo Park (2011)
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
Bölöni, L. (2014). Autobiography Based Prediction in a Situated AGI Agent. 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_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-09274-4_2
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09273-7
Online ISBN: 978-3-319-09274-4
eBook Packages: Computer ScienceComputer Science (R0)