Four principal features of autonomous control systems are left both unaddressed and unaddressable by present-day engineering methodologies: (1) The ability to operate effectively in environments that are only partially known at design time; (2) A level of generality that allows a system to re-assess and re-define the fulfillment of its mission in light of unexpected constraints or other unforeseen changes in the environment; (3) The ability to operate effectively in environments of significant complexity; and (4) The ability to degrade gracefully—how it can continue striving to achieve its main goals when resources become scarce, or in light of other expected or unexpected constraining factors that impede its progress. We describe new methodological and engineering principles for addressing these shortcomings, that we have used to design a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates. The work provides an architectural blueprint for constructing systems with high levels of operational autonomy in underspecified circumstances, starting from only a small amount of designer-specified code—a seed. Using value-driven dynamic priority scheduling to control the parallel execution of a vast number of lines of reasoning, the system accumulates increasingly useful models of its experience, resulting in recursive self-improvement that can be autonomously sustained after the machine leaves the lab, within the boundaries imposed by its designers. A prototype system named AERA has been implemented and demonstrated to learn a complex real-world task—real-time multimodal dialogue with humans—by on-line observation. Our work presents solutions to several challenges that must be solved for achieving artificial general intelligence.
KeywordsGeneral Intelligence Composite State Goto Step Core Operation Instantiate Model
Unable to display preview. Download preview PDF.
- 1.Nivel, E., Thórisson, K.R., Steunebrink, B.R., Dindo, H., Pezzulo, G., Rodríguez, M., Hernández, C., Ognibene, D., Schmidhuber, J., Sanz, R., Helgason, H.P., Chella, A., Jonsson, G.K.: Bounded Recursive Self-Improvement. Tech. Rep. RUTR-SCS13006, Reykjavik University (2013), http://arxiv.org/abs/1312.6764
- 4.Simon, H.: A Behavioral Model of Rational Choice. In: Models of Man, Social and Rational: Mathematical Essays on Rational Human Behavior in a Social Setting. Wiley, NY (1957)Google Scholar
- 5.Thórisson, K.R.: Methodology Matters: Constructionism Challenged, Constructivism Challenges (forthcoming)Google Scholar
- 6.Thórisson, K.R.: A New Constructivist AI: From Manual Construction to Self-Constructive Systems. In: Wang, P., Goertzel, B. (eds.) Theoretical Foundations of Artificial General Intelligence. Atlantis Thinking Machines, vol. 4, pp. 145–171 (2012)Google Scholar
- 7.Thórisson, K.R.: From Constructionist to Constructivist A.I. Keynote, AAAI Fall Symposium Series – Biologically Inspired Cognitive Architectures, Washington D.C., November 5-7, 175-183. AAAI Tech Report FS-09-01. AAAI Press, Menlo Park, CA (2009)Google Scholar
- 8.Nivel, E., Thórisson, K.R.: Self-Programming: Operationalizing Autonomy. In: Proceedings of the Second Conference on Artificial General Intelligence (2009)Google Scholar
- 9.Thórisson, K.R., Nivel, E.: Holistic Intelligence: Transversal Skills and Current Methodologies. In: Proc. of the 2nd Conf. on Artificial General Intelligence (AGI 2009), pp. 220–221 (2009)Google Scholar
- 11.Thórisson, K.R., Nivel, E.: Achieving Artificial General Intelligence Through Peewee Granularity. In: Proc. of the 2nd Conf. on Artificial General Intelligence (AGI 2009), pp. 222–223 (2009)Google Scholar
- 12.Nivel, E., Thórisson, K.R.: Prosodica Real-Time Prosody Tracker. Reykjavik University School of Computer Science Technical Report RUTR08002 (2008)Google Scholar
- 13.Nivel, E., Thórisson, K.R.: Seed Specification for AERA S1 in Experiments 1 & 2. Reykjavik University School of Computer Science Technical Report, RUTR-SCS13005 (2013)Google Scholar