{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:45:56Z","timestamp":1760150756933,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T00:00:00Z","timestamp":1703721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Games"],"abstract":"<jats:p>In this article, we investigate the relative performance of artificial neural networks and structural models of decision theory by training 69 artificial intelligence models on a dataset of 7080 human decisions in extensive form games. The objective is to compare the predictive power of AIs that use a representation of another agent\u2019s decision-making process in order to improve their own performance during a strategic interaction. We use human game theory data for training and testing. Our findings hold implications for understanding how AIs can use constrained structural representations of other decision makers, a crucial aspect of our \u2018Theory of Mind\u2019. We show that key psychological features, such as the Weber\u2013Fechner law for economics, are evident in our tests, that simple linear models are highly robust, and that being able to switch between different representations of another agent is a very effective strategy. Testing different models of AI-ToM paves the way for the development of learnable abstractions for reasoning about the mental states of \u2018self\u2019 and \u2018other\u2019, thereby providing further insights for fields such as social robotics, virtual assistants, and autonomous vehicles, and fostering more natural interactions between people and machines.<\/jats:p>","DOI":"10.3390\/g15010001","type":"journal-article","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T09:35:21Z","timestamp":1703756121000},"page":"1","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Testing Game Theory of Mind Models for Artificial Intelligence"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2199-2515","authenticated-orcid":false,"given":"Michael S.","family":"Harr\u00e9","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney, Sydney 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Husam","family":"El-Tarifi","sequence":"additional","affiliation":[{"name":"Independent Researcher, Sydney 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1209\/epl\/i2000-00208-x","article-title":"Collective intelligence for control of distributed dynamical systems","volume":"49","author":"Wolpert","year":"2000","journal-title":"EPL (Europhys. Lett.)"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3368986","article-title":"Frameworks for collective intelligence: A systematic literature review","volume":"53","author":"Suran","year":"2020","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1038\/s44159-022-00054-y","article-title":"Information aggregation and collective intelligence beyond the wisdom of crowds","volume":"1","author":"Kameda","year":"2022","journal-title":"Nat. Rev. Psychol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"20200315","DOI":"10.1098\/rstb.2020.0315","article-title":"Collective minds: Social network topology shapes collective cognition","volume":"377","author":"Momennejad","year":"2022","journal-title":"Philos. Trans. R. Soc. B"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20160044","DOI":"10.1098\/rsif.2016.0044","article-title":"The social brain: Scale-invariant layering of Erd\u0151s\u2013R\u00e9nyi networks in small-scale human societies","volume":"13","author":"Prokopenko","year":"2016","journal-title":"J. R. Soc. Interface"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1126\/science.1193147","article-title":"Evidence for a collective intelligence factor in the performance of human groups","volume":"330","author":"Woolley","year":"2010","journal-title":"Science"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1016\/S0896-6273(01)00552-9","article-title":"Mind blindness and the brain in autism","volume":"32","author":"Frith","year":"2001","journal-title":"Neuron"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5077","DOI":"10.1073\/pnas.1618722114","article-title":"Optimal incentives for collective intelligence","volume":"114","author":"Mann","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yoshida, W., Dolan, R.J., and Friston, K.J. (2008). Game theory of mind. PLoS Comput. Biol., 4.","DOI":"10.1371\/journal.pcbi.1000254"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1126\/science.ade9097","article-title":"Human-level play in the game of Diplomacy by combining language models with strategic reasoning","volume":"378","author":"Team","year":"2022","journal-title":"Science"},{"key":"ref_11","first-page":"1367","article-title":"Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory","volume":"32","author":"Dawid","year":"2004","journal-title":"Ann. Stat."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"036102","DOI":"10.1103\/PhysRevE.85.036102","article-title":"Hysteresis effects of changing the parameters of noncooperative games","volume":"85","author":"Wolpert","year":"2012","journal-title":"Phys. Rev. E"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ruiz-Serra, J., and Harr\u00e9, M.S. (2023). Inverse Reinforcement Learning as the Algorithmic Basis for Theory of Mind: Current Methods and Open Problems. Algorithms, 16.","DOI":"10.3390\/a16020068"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1038\/nn2065","article-title":"Game theory and neural basis of social decision making","volume":"11","author":"Lee","year":"2008","journal-title":"Nat. Neurosci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.tins.2015.11.002","article-title":"Neural basis of strategic decision making","volume":"39","author":"Lee","year":"2016","journal-title":"Trends Neurosci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103216","DOI":"10.1016\/j.artint.2019.103216","article-title":"The hanabi challenge: A new frontier for ai research","volume":"280","author":"Bard","year":"2020","journal-title":"Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1016\/j.tics.2022.08.003","article-title":"Planning with theory of mind","volume":"26","author":"Ho","year":"2022","journal-title":"Trends Cogn. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Harr\u00e9, M.S. (2022). What Can Game Theory Tell Us about an AI \u2018Theory of Mind\u2019?. Games, 13.","DOI":"10.3390\/g13030046"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"112421","DOI":"10.1016\/j.bbr.2019.112421","article-title":"Active inference, stressors, and psychological trauma: A neuroethological model of (mal) adaptive explore-exploit dynamics in ecological context","volume":"380","author":"Linson","year":"2020","journal-title":"Behav. Brain Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.newideapsych.2017.09.002","article-title":"\u201cHow do humans make sense?\u201d multiscale dynamics and emergent meaning","volume":"50","author":"Dale","year":"2018","journal-title":"New Ideas Psychol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.neunet.2019.08.007","article-title":"Neural dynamics of emotion and cognition: From trajectories to underlying neural geometry","volume":"120","author":"Pessoa","year":"2019","journal-title":"Neural Netw."},{"key":"ref_22","unstructured":"Nowak, A. (2016). Theory Construction in Social Personality Psychology, Psychology Press."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"117844","DOI":"10.1016\/j.neuroimage.2021.117844","article-title":"Whole-brain modelling of resting state fMRI differentiates ADHD subtypes and facilitates stratified neuro-stimulation therapy","volume":"231","author":"Iravani","year":"2021","journal-title":"Neuroimage"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1038\/s41583-022-00642-0","article-title":"Attractor and integrator networks in the brain","volume":"23","author":"Khona","year":"2022","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1970","DOI":"10.1038\/s41593-023-01445-x","article-title":"Attractor dynamics reflect decision confidence in macaque prefrontal cortex","volume":"26","author":"Wang","year":"2023","journal-title":"Nat. Neurosci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1016\/j.cub.2016.04.063","article-title":"Hippocampal attractor dynamics predict memory-based decision making","volume":"26","author":"Steemers","year":"2016","journal-title":"Curr. Biol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Harr\u00e9, M.S. (2021). Information theory for agents in artificial intelligence, psychology, and economics. Entropy, 23.","DOI":"10.3390\/e23030310"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e13226","DOI":"10.1111\/cogs.13226","article-title":"Extracting low-dimensional psychological representations from convolutional neural networks","volume":"47","author":"Jha","year":"2023","journal-title":"Cogn. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1111\/tops.12453","article-title":"The dynamics of neural populations capture the laws of the mind","volume":"12","year":"2020","journal-title":"Top. Cogn. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1126\/science.abe2629","article-title":"Using large-scale experiments and machine learning to discover theories of human decision-making","volume":"372","author":"Peterson","year":"2021","journal-title":"Science"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"257","DOI":"10.3390\/g2030257","article-title":"A choice prediction competition for social preferences in simple extensive form games: An introduction","volume":"2","author":"Ert","year":"2011","journal-title":"Games"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1162\/003355399556151","article-title":"A theory of fairness, competition, and cooperation","volume":"114","author":"Fehr","year":"1999","journal-title":"Q. J. Econ."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1162\/biot.2006.1.2.123","article-title":"The foundations of behavior: The beliefs, preferences, and constraints model","volume":"1","author":"Gintis","year":"2006","journal-title":"Biol. Theory"},{"key":"ref_34","first-page":"14","article-title":"Perception matters: Psychophysics for economists","volume":"2","author":"Weber","year":"2004","journal-title":"Psychol. Econ. Decis."}],"container-title":["Games"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4336\/15\/1\/1\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:43:24Z","timestamp":1760132604000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4336\/15\/1\/1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,28]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["g15010001"],"URL":"https:\/\/doi.org\/10.3390\/g15010001","relation":{},"ISSN":["2073-4336"],"issn-type":[{"type":"electronic","value":"2073-4336"}],"subject":[],"published":{"date-parts":[[2023,12,28]]}}}