DEMONSTRATING SENSEMAKING EMERGENCE IN ARTIFICIAL AGENTS: A METHOD AND AN EXAMPLE
Abstract
We propose an experimental method to study the possible emergence of sensemaking in artificial agents. This method involves analyzing the agent's behavior in a test bed environment that presents regularities in the possibilities of interaction afforded to the agent, while the agent has no presuppositions about the underlying functioning of the environment that explains such regularities. We propose a particular environment that permits such an experiment, called the Small Loop Problem. We argue that the agent's behavior demonstrates sensemaking if the agent learns to exploit regularities of interaction to fulfill its self-motivation as if it understood (at least partially) the underlying functioning of the environment. As a corollary, we argue that sensemaking and self-motivation come together. We propose a new method to generate self-motivation in an artificial agent called interactional motivation. An interactionally motivated agent seeks to perform interactions with predefined positive values and avoid interactions with predefined negative values. We applied the proposed sensemaking emergence demonstration method to an agent implemented previously, and produced example reports that suggest that this agent is capable of a rudimentary form of sensemaking.
References
- J. Math. Anal. Appl. (10) 174 ( 1965 ) . Crossref, ISI, Google Scholar
D. Blank , J. Lewis and J. Marshall , The multiple roles of anticipation in developmental robotics, Proc. AAAI 2005 Fall Symposium: From Reactive to Anticipatory Cognitive Embodied Systems (2005) pp. 8–14. Google ScholarO. L. Georgeon and J. B. Marshall , The small loop problem: A challenge for artificial emergent cognition, Proc. Biologically Inspired Cognitive Architectures (2012) pp. 137–144. Google ScholarO. L. Georgeon , J. B. Marshall and S. Gay , Interactional motivation in artificial systems: Between extrinsic and intrinsic motivation, Proc. Int. Conf. Development and Learning (EPIROB'2012) (San Diego, CA, 2012) pp. 1–2. Google Scholar- Cogn. Sys. Res. 16 , 73 ( 2012 ) . Crossref, ISI, Google Scholar
-
W. James , Pragmatism ( Dover Publications , New York , 1907 ) . Google Scholar - IEEE Transact. Evol. Comput. 11(2), 265 (2007). Crossref, ISI, Google Scholar
-
R. Pfeifer and S. Bongard , How the Body Shapes the Way We Think: A New View of Intelligence ( Cambridge, MA , 2006 ) . Crossref, Google Scholar - , From Perception to Action, eds.
P. Gaussier and J.-D. Nicoud (IEEE Computer Society Press, 1994) pp. 1–11. Crossref, Google Scholar -
J. Piaget , The Psychology of Intelligence ( Routledge and Kegan Paul , London , 1951 ) . Google Scholar - J. Artif. Gen. Intel. 2 , 1 ( 2010 ) . Crossref, ISI, Google Scholar
- Biol. Insp. Cogn. Arch. 1 , 100 ( 2012 ) . Google Scholar
- IEEE Transact. Autonomous Mental Development 2(3), 230 (2010). Crossref, ISI, Google Scholar
- , Embodied Artificial Intelligence, eds.
I. Fumiya (Springer Verlag, Berlin, 2004) pp. 231–242. Crossref, Google Scholar -
L. A. Suchman , Plans and Situated Actions ( Cambridge University Press , Cambridge , 1987 ) . Google Scholar -
R. Sun and C. L. Giles , Sequence Learning — Paradigms, Algorithms, and Applications 1828 ( Springer , Berlin, Heidelberg , 2000 ) . Google Scholar - Wilensky, U. [1999] NetLogo. http://ccl.northwestern.edu/netlogo/. Center for Connected Learning and Computer-Based Modeling, Northwestern University, Evanston, IL . Google Scholar
-
L. Wittgenstein , Philosophical Investigations ( Blackwell Publishing , Malden, MA , 1953 ) . Google Scholar
