{"type":"ScholarlyArticle","title":"Why Bad Coffee? Explaining BDI Agent Behaviour with Valuings (Extended Abstract)","authors":[{"name":"Michael Winikoff","slug":"michael-winikoff","given":"Michael","family":"Winikoff","affiliation":"Victoria University of Wellington"},{"name":"Galina Sidorenko","slug":"galina-sidorenko","given":"Galina","family":"Sidorenko","affiliation":"Halmstad University"},{"name":"Virginia Dignum","slug":"virginia-dignum","given":"Virginia","family":"Dignum","affiliation":"Umeå University"},{"name":"Frank Dignum","slug":"frank-dignum","given":"Frank","family":"Dignum","affiliation":"Umeå University"}],"abstract":"An important issue in deploying an autonomous system is how to enable human users and stakeholders to develop an appropriate level of trust in the system. It has been argued that a crucial mechanism to enable appropriate trust is the ability of a system to explain its behaviour. Obviously, such explanations need to be comprehensible to humans. Due to the perceived similarity in functioning between humans and autonomous systems, we argue that it makes sense to build on the results of extensive research in social sciences that explores how humans explain their behaviour. Using similar concepts for explanation is argued to help with comprehensibility, since the concepts are familiar. Following work in the social sciences, we propose the use of a folk-psychological model that utilises beliefs, desires, and ``valuings''. We propose a formal framework for constructing explanations of the behaviour of an autonomous system, present an (implemented) algorithm for giving explanations, and present evaluation results.","doi":"10.24963/ijcai.2022/810","url":"https://ijcai.org/proceedings/2022/810","pdf":"https://ijcai.org/proceedings/2022/0810.pdf","markdown":"https://ijcai.org/proceedings/2022/810.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/810","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Journal Track","track":"Journal Track","number":810,"pages":{"first":5782,"last":5786},"keywords":["AI Ethics, Trust, Fairness: Values","AI Ethics, Trust, Fairness: Explainability and Interpretability","AI Ethics, Trust, Fairness: General","Agent-based and Multi-agent Systems: Agent Theories and Models","AI Ethics, Trust, Fairness: Trustworthy AI"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987233","length_sec":89,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985376","length_sec":698,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bratman et al., 1988] M. E. Bratman, D. J. Israel, and M. E. Pollack. Plans and resource-bounded practical reasoning. Computational Intelligence, 4:349-355, 1988.","title":"Plans and resource-bounded practical reasoning","authors":"M E Bratman, D J Israel, M E Pollack","year":"1988","venue":"Computational Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bratman, 1987] Michael E. Bratman. Intentions, Plans, and Practical Reason. Harvard University Press, Cambridge, MA, 1987.","title":"Intentions, Plans, and Practical Reason","authors":"E Michael, Bratman","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cranefield et al., 2017] Stephen Cranefield, Michael Winikoff, Virginia Dignum, and Frank Dignum. No Pizza for You: Value-based Plan Selection in BDI Agents. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 178-184, 2017.","title":"No Pizza for You: Value-based Plan Selection in BDI Agents","authors":"Stephen Cranefield, Michael Winikoff, Virginia Dignum, Frank Dignum","year":"2017","venue":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17","doi":null,"url":null,"internal_url":"/proceedings/2017/26"},{"position":4,"raw":"[de Graaf and Malle, 2019] Maartje M. A. de Graaf and Bertram F. Malle. People's Explanations of Robot Be- havior Subtly Reveal Mental State Inferences. In 14th ACM/IEEE International Conference on Human-Robot In- teraction, HRI 2019, Daegu, South Korea, March 11-14, 2019, pages 239-248. IEEE, 2019.","title":"People's Explanations of Robot Behavior Subtly Reveal Mental State Inferences","authors":"M A Maartje, Bertram F De Graaf, Malle","year":"2019","venue":"14th ACM/IEEE International Conference on Human-Robot Interaction","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Harbers, 2011] Maaike Harbers. Explaining Agent Behav- ior in Virtual Training. SIKS dissertation series no. 2011- 35, SIKS (Dutch Research School for Information and Knowledge Systems), 2011.","title":"Explaining Agent Behavior in Virtual Training","authors":"Maaike Harbers","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Malle, 2004] Bertram F. Malle. How the Mind Explains Be- havior: Folk Explanations, Meaning, and Social Interac- tion. The MIT Press, 2004. ISBN 0-262-13445-4.","title":"How the Mind Explains Behavior: Folk Explanations, Meaning, and Social Interaction","authors":"F Bertram, Malle","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Rao and Georgeff, 1992] Anand S. Rao and Michael P. Georgeff. An abstract architecture for rational agents. In C. Rich, W. Swartout, and B. Nebel, editors, Proceed- ings of the Third International Conference on Principles of Knowledge Representation and Reasoning, pages 439- 449, San Mateo, CA, 1992.","title":"An abstract architecture for rational agents","authors":"Anand S Rao, Michael P Georgeff","year":"1992","venue":"Proceedings of the Third International Conference on Principles of Knowledge Representation and Reasoning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Morgan Kaufmann Publishers. [Thellman et al., 2017] Sam Thellman, Annika Silvervarg, and Tom Ziemke. Folk-Psychological Interpretation of Human vs. Humanoid Robot Behavior: Exploring the In- tentional Stance toward Robots. Frontiers in Psychology, 8:1-14, 2017.","title":"Folk-Psychological Interpretation of Human vs. Humanoid Robot Behavior: Exploring the Intentional Stance toward Robots","authors":"Morgan Kaufmann, Publishers Thellman","year":"2017","venue":"Frontiers in Psychology","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Winikoff and Sidorenko, 2021] Michael Winikoff and Galina Sidorenko. Evaluating a mechanism for ex- plaining BDI agent behaviour. https://profwinikoff.files. wordpress.com/2021/07/evaluating.pdf, 2021. Accessed: 2022-06-01.","title":"Evaluating a mechanism for explaining BDI agent behaviour","authors":"Sidorenko Winikoff, Michael Winikoff, Galina Sidorenko","year":"2021","venue":null,"doi":null,"url":"https://profwinikoff.files.wordpress.com/2021/07/evaluating.pdf","internal_url":null},{"position":10,"raw":"[Winikoff et al., 2018] Michael Winikoff, Virginia Dignum, and Frank Dignum. Why bad coffee? Explaining agent plans with valuings. In Barbara Gallina, Amund Skavhaug, Erwin Schoitsch, and Friedemann Bitsch, ed- itors, Computer Safety, Reliability, and Security -SAFE- COMP 2018 Workshops, ASSURE, DECSoS, SASSUR, STRIVE, and WAISE, Västerås, Sweden, September 18, 2018, Proceedings, volume 11094 of Lecture Notes in Computer Science, pages 521-534. Springer, 2018.","title":"Why bad coffee? Explaining agent plans with valuings","authors":"Michael Winikoff, Virginia Dignum, Frank Dignum","year":"2018","venue":"and Security -SAFE-COMP 2018 Workshops, ASSURE, DECSoS, SASSUR, STRIVE, and WAISE","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Winikoff et al., 2021] Michael Winikoff, Galina Sidorenko, Virginia Dignum, and Frank Dignum. Why bad coffee? explaining BDI agent behaviour with valuings. Artif. In- tell., 300:103554, 2021.","title":"Why bad coffee? explaining BDI agent behaviour with valuings","authors":"Michael Winikoff, Galina Sidorenko, Virginia Dignum, Frank Dignum","year":"2021","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}