Abstract
Adult humans are typically capable of impressive, often recursive, reasoning about the mental states of others, but recent evidence has suggested that said reasoning, called Theory of Mind reasoning (ToM), is not easy or automatic. This has lead to the theory that human ToM reasoning requires two systems. One system, efficient but inflexible, enables rapid judgements by operating without explicit modeling of beliefs, while a separate, effortful system, enables richer predictions over more complex belief encodings. We argue that computational ToM requires a similar distinction. However, we propose a different model: a single process, but with effortful re-representation leading to two phases of ToM reasoning. Efficient reasoning, in our view, occurs over representations that include actions, but not necessarily explicit belief states. Effortful reasoning, then, involves re-representation of these initial encodings in order to handle errors, resolve real-world conflicts, and fully account for others’ belief states. We present an implemented computational model, based in memory retrieval and structural alignment, and discuss possible implications for computational agents in human-machine teams.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Apperly, I.A., Butterfill, S.A.: Do humans have two systems to track beliefs and belief-like states? Psychol. Rev. 116(4), 953 (2009)
Apperly, I.A., Riggs, K.J., Simpson, A., Chiavarino, C., Samson, D.: Is belief reasoning automatic? Psychol. Sci. 17(10), 841–844 (2006)
Borck, H., Karneeb, J., Floyd, M.W., Alford, R., Aha, D.W.: Case-based policy and goal recognition. In: Hüllermeier, E., Minor, M. (eds.) ICCBR 2015. LNCS (LNAI), vol. 9343, pp. 30–43. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24586-7_3
Eger, M., Martens, C., Chacón, P.S., Córdoba, M.A., Cespedes, J.H.: Operationalizing intentionality to play Hanabi with human players. IEEE Trans. Games (2020)
Forbus, K.D., Ferguson, R.W., Lovett, A., Gentner, D.: Extending SME to handle large-scale cognitive modeling. Cogn. Sci. 41(5), 1152–1201 (2017)
Forbus, K.D., Gentner, D., Law, K.: Mac/fac: a model of similarity-based retrieval. Cogn. Sci. 19(2), 141–205 (1995)
Geib, C., Weerasinghe, J., Matskevich, S., Kantharaju, P., Craenen, B., Petrick, R.P.A.: Building helpful virtual agents using plan recognition and planning. In: Proceedings of the 12th AAAI Conference on AIIDE, pp. 162–168 (2016)
Gentner, D.: Structure-mapping: a theoretical framework for analogy. Cogn. Sci. 7(2), 155–170 (1983)
Hiatt, L.M., Harrison, A.M., Trafton, J.G.: Accommodating human variability in human-robot teams through theory of mind. In: Twenty-Second International Joint Conference on Artificial Intelligence (2011)
Höller, D., Behnke, G., Bercher, P., Biundo, S.: Plan and goal recognition as HTN planning. In: Proceedings of the 30th IEEE International Conference on Tools with Artificial Intelligence, pp. 466–473 (2018)
Kantharaju, P., Ontañón, S., Geib, C.W.: Scaling up CCG-based plan recognition via Monte-Carlo tree search. In: Proceedings of the 2019 IEEE-COG, pp. 1–8 (2019)
Keysar, B., Barr, D.J., Balin, J.A., Brauner, J.S.: Taking perspective in conversation: the role of mutual knowledge in comprehension. Psychol. Sci. 11(1), 32–38 (2000)
Keysar, B., Lin, S., Barr, D.J.: Limits on theory of mind use in adults. Cognition 89(1), 25–41 (2003)
Kovács, Á.M., Téglás, E., Csibra, G.: Can infants adopt underspecified contents into attributed beliefs? representational prerequisites of theory of mind. Cognition 214, 104640 (2021)
Lin, S., Keysar, B., Epley, N.: Reflexively mindblind: using theory of mind to interpret behavior requires effortful attention. J. Exp. Soc. Psychol. 46(3), 551–556 (2010)
Markman, A.B., Gentner, D.: Commonalities and differences in similarity comparisons. Mem. Cogn. 24(2), 235–249 (1996)
Mirsky, R., Keren, S., Geib, C.: Introduction to symbolic plan and goal recognition. Synth. Lect. Artif. Intell. Mach. Learn. 16(1), 1–190 (2021)
Mostafazadeh, N., et al.: GLUCOSE: generalized and contextualized story explanations. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4569–4586. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.emnlp-main.370, https://aclanthology.org/2020.emnlp-main.370
Onishi, K.H., Baillargeon, R.: Do 15-month-old infants understand false beliefs? Science 308(5719), 255–258 (2005)
Puig, X., et al.: Watch-and-help: a challenge for social perception and human-AI collaboration. In: International Conference on Learning Representations (2020)
Rabkina, I., Forbus, K.D.: Analogical reasoning for intent recognition and action prediction in multi-agent systems. In: Proceedings of the Seventh Annual Conference on Advances in Cognitive Systems, pp. 504–517 (2019)
Rabkina, I., Kantharaju, P., Roberts, M., Wilson, J., Forbus, K., Hiatt, L.M.: Recognizing the goals of uninspectable agents. In: Advances in Cognitive Systems (2020)
Rabkina, I., McFate, C., Forbus, K.D., Hoyos, C.: Towards a computational analogical theory of mind. In: Proceedings of the 39th Annual Meeting of the Cognitive Science Society (2017)
Rabkina, I., McFate, C.J., Forbus, K.D.: Bootstrapping from language in the analogical theory of mind model. In: CogSci (2018)
Ramirez, M., Geffner, H.: Goal recognition over POMDPs: Inferring the intention of a POMDP agent. In: Twenty-Second International Joint Conference on Artificial Intelligence (2011)
Shum, M., Kleiman-Weiner, M., Littman, M.L., Tenenbaum, J.B.: Theory of minds: understanding behavior in groups through inverse planning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6163–6170 (2019)
Villiers, J.G.: The Role(s) of language in theory of mind. In: Gilead, M., Ochsner, K.N. (eds.) The Neural Basis of Mentalizing, pp. 423–448. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-51890-5_21
Wellman, H.M., Liu, D.: Scaling of theory-of-mind tasks. Child Develop. 75(2), 523–541 (2004)
Wilson, J.R., Gilpin, L., Rabkina, I.: A knowledge driven approach to adaptive assistance using preference reasoning and explanation. In: AAAI Fall Symposium on Artificial Intelligence for Human-Robot Interaction (AI-HRI) (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rabkina, I., McFate, C. (2022). Should Agents Have Two Systems to Track Beliefs and Belief-Like States?. In: Gurney, N., Sukthankar, G. (eds) Computational Theory of Mind for Human-Machine Teams. AAAI-FSS 2021. Lecture Notes in Computer Science, vol 13775. Springer, Cham. https://doi.org/10.1007/978-3-031-21671-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-21671-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21670-1
Online ISBN: 978-3-031-21671-8
eBook Packages: Computer ScienceComputer Science (R0)