A THEORETICAL FRAMEWORK FOR EXPLAINING AGENT BEHAVIOR

Maaike Harbers, Karel van den Bosch, John-Jules Meyer

2011

Abstract

To understand emergent processes in multi-agent-based simulations it is important to study the global processes in a simulation as well as the processes on the agent level. The behavior of individual agents is easier to understand when they are able to explain their own behavior. In this paper, a theoretical framework for explaining agent behavior is proposed. By distinguishing different types and contexts of explanations, the framework aims to support the development of explainable agents. The framework is based on an examination of explanation literature, and experiences with developing explainable agents for virtual training. The use of the framework is illustrated by an example about the development of a negotiation agent.

References

  1. Atkinson, K., Bench-Capon, T., and McBurney, P. (2006). Computational representation of practical argument. Synthese, 152(2):157-206.
  2. Core, M., Lane, H., Van Lent, M., Gomboc, D., Solomon, S., and Rosenberg, M. (2006). Building explainable artificial intelligence systems. In AAAI.
  3. Gomboc, D., Solomon, S., Core, M. G., Lane, H. C., and van Lent, M. (2005). Design recommendations to support automated explanation and tutoring. In Proc. of BRIMS 2005, Universal City, CA.
  4. Harbers, M., Bosch, K. v. d., and Meyer, J.-J. (2010a). Design and evaluation of explainable BDI agents. In Proceedings of IAT 2010, volume 2, pages 125-132.
  5. Harbers, M., Bosch, K. v. d., and Meyer, J.-J. (2010b). Explaining simulations through self explaining agents. Journal of Artificial Societies and Social Simulation, 12(1)(4).
  6. Johnson, L. (1994). Agents that learn to explain themselves. In Proceedings of the Conference on AI, pages 1257- 1263.
  7. Malle, B. (1999). How people explain behavior: A new theoretical framework. Personality and Social Psychology Review, 3(1):23-48.
  8. Van Lent, M., Fisher, W., and Mancuso, M. (2004). An explainable artificial intelligence system for small-unit tactical behavior. In Proc. of IAAA 2004, Menlo Park, CA. AAAI Press.
Download


Paper Citation


in Harvard Style

Harbers M., van den Bosch K. and Meyer J. (2011). A THEORETICAL FRAMEWORK FOR EXPLAINING AGENT BEHAVIOR . In Proceedings of 1st International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH, ISBN 978-989-8425-78-2, pages 228-231. DOI: 10.5220/0003620102280231


in Bibtex Style

@conference{simultech11,
author={Maaike Harbers and Karel van den Bosch and John-Jules Meyer},
title={A THEORETICAL FRAMEWORK FOR EXPLAINING AGENT BEHAVIOR},
booktitle={Proceedings of 1st International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,},
year={2011},
pages={228-231},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003620102280231},
isbn={978-989-8425-78-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of 1st International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,
TI - A THEORETICAL FRAMEWORK FOR EXPLAINING AGENT BEHAVIOR
SN - 978-989-8425-78-2
AU - Harbers M.
AU - van den Bosch K.
AU - Meyer J.
PY - 2011
SP - 228
EP - 231
DO - 10.5220/0003620102280231