Abstract
In this paper we focus on explaining to humans the behavior of autonomous agents, i.e., explainable agents. Explainable agents are useful for many reasons including scenario-based training (e.g. disaster training), tutor and pedagogical systems, agent development and debugging, gaming, and interactive storytelling. As the aim is to generate for humans plausible and insightful explanations, user evaluation of different explanations is essential. In this paper we test the hypothesis that different explanation types are needed to explain different types of actions. We present three different, generically applicable, algorithms that automatically generate different types of explanations for actions of BDI-based agents. Quantitative analysis of a user experiment (n=30), in which users rated the usefulness and naturalness of each explanation type for different agent actions, supports our hypothesis. In addition, we present feedback from the users about how they would explain the actions themselves. Finally, we hypothesize guidelines relevant for the development of explainable BDI agents.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Cortellessa, G., Cesta, A.: Evaluating mixed-initiative systems: An experimental approach. In: ICAPS’06, pp. 172–181 (2006)
Gilbert, N.: Explanation and dialogue. The Knowledge Engineering Review 4(03), 235–247 (1989) 10.1017/S026988890000504X
Core, M., Traum, T., Lane, H., Swartout, W., Gratch, J., Van Lent, M.: Teaching negotiation skills through practice and reflection with virtual humans. Simulation 82(11), 685–701 (2006)
Graesser, A.C., Chipman, P., Haynes, B.C., Olney, A.: Autotutor: an intelligent tutoring system with mixed-initiative dialogue. IEEE Transactions on Education 48(4), 612–618 (2005)
Broekens, J., DeGroot, D.: Formalizing cognitive appraisal: from theory to computation. In: Trapple, R. (ed.) Cybernetics and Systems 2006, Vienna, Austrian, Society for Cybernetics Studies, pp. 595–600 (2006)
Cavazza, M., Charles, F., Mead, S.J.: Character-based interactive storytelling. IEEE Intelligent Systems 17(4), 17–24 (2002)
Theune, M., Faas, S., Heylen, D.K.J., Nijholt, A.: The virtual qstoryteller: Story creation by intelligent agents. In: TIDSE 2003: Technologies for Interactive Digital Storytelling and Entertainment, Darmstadt, pp. 204–215. Fraunhofer IRB Verlag (2003)
Keil, F.: Explanation and understanding. Annual Reviews Psychology 57, 227–254 (2006)
Harbers, M., Van den Bosch, K., Meyer, J.: A study into preferred explanations of virtual agent behavior. In: Ruttkay, Z., Kipp, M., Nijholt, A., Vilhjálmsson, H. (eds.) IVA 2009. LNCS, vol. 5773, pp. 132–145. Springer, Heidelberg (2009)
Johnson, W.: Agents that learn to explain themselves. In: Proc. of the 12th Nat. Conf. on Artificial Intelligence, pp. 1257–1263 (1994)
Van Lent, M., Fisher, W., Mancuso, M.: An explainable artificial intelligence system for small-unit tactical behavior. In: Proc. of IAAA 2004. AAAI Press, Menlo Park (2004)
Gomboc, D., Solomon, S., Core, M.G., Lane, H.C., van Lent, M.: Design recommendations to support automated explanation and tutoring. In: Proc. of BRIMS 2005, Universal City, CA (2005)
Core, M., Lane, H., Van Lent, M., Gomboc, D., Solomon, S., Rosenberg, M.: Building explainable artificial intelligence systems. In: AAAI (2006)
Hindriks, K.: Programming Rational Agents in GOAL. In: Multi-Agent Programming: Languages, Tools and Applications, pp. 119–157. Springer, Heidelberg (2009)
Schraagen, J., Chipman, S., Shalin, V. (eds.): Cognitive Task Analysis. Lawrence Erlbaum Associates, Mahway (2000)
Malle, B.: How people explain behavior: A new theoretical framework. Personality and Social Psychology Review 3(1), 23–48 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Broekens, J., Harbers, M., Hindriks, K., van den Bosch, K., Jonker, C., Meyer, JJ. (2010). Do You Get It? User-Evaluated Explainable BDI Agents. In: Dix, J., Witteveen, C. (eds) Multiagent System Technologies. MATES 2010. Lecture Notes in Computer Science(), vol 6251. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16178-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-16178-0_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16177-3
Online ISBN: 978-3-642-16178-0
eBook Packages: Computer ScienceComputer Science (R0)