{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T11:47:15Z","timestamp":1791373635323,"version":"4.3.1"},"reference-count":36,"publisher":"The Royal Society","issue":"12","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":281,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":281,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":281,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":281,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":281,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["royalsocietypublishing.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Electricity competition, restrictions on carbon dioxide (CO2) emissions and arm races between nations are examples of social dilemmas within human society. In the presence of social dilemmas, rational choice in game theory leads to the avoidance of cooperative behaviour owing to its cost. However, in experiments using public goods games that simulate social dilemmas, humans have often exhibited cooperative behaviour that deviates from individual rationality. Despite extensive research, the alignment between human cooperative behaviour and game theory predictions remains inconsistent. This study proposes an alternative approach to solve this problem. We used Q-learning, a form of artificial intelligence that mimics decision-making processes of humans who do not possess the rationality assumed in game theory. This study explores the potential for cooperation by varying the number of participants in public goods games using deep Q-learning. The simulations demonstrate that agents with Q-learning can acquire cooperative behaviour similar to that of humans. Moreover, we found that cooperation is more likely to occur as the group size increases. These results support and reinforce existing experiments involving humans. In addition, they have potential applications for creating cooperation without sanctions.<\/jats:p>","DOI":"10.1098\/rsos.241195","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T19:10:54Z","timestamp":1733857854000},"update-policy":"https:\/\/doi.org\/10.1098\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Analysing public goods games using reinforcement learning: effect of increasing group size on cooperation"],"prefix":"10.1098","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9992-8158","authenticated-orcid":true,"given":"Kazuhiro","family":"Tamura","sequence":"first","affiliation":[{"name":"Department of Environment and Energy Systems, Graduate School of Science and Technology, Shizuoka University, Hamamatsu 432-8561, Japan 1"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-6218","authenticated-orcid":true,"given":"Satoru","family":"Morita","sequence":"additional","affiliation":[{"name":"Department of Mathematical and Systems Engineering, Shizuoka University, Hamamatsu 432-8561, Japan 2"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"2026010719422531100_B1","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1257\/aer.90.4.980","article-title":"Cooperation and punishment in public goods experiments","volume":"90","author":"Fehr","year":"2000","journal-title":"Am. Econ. Rev."},{"key":"2026010719422531100_B2","first-page":"540","volume-title":"Social psychology: handbook of basic principles, 2nd edn","author":"Lange","year":"2007"},{"key":"2026010719422531100_B3","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1111\/1467-9442.00182","article-title":"Conditional cooperation and voluntary contributions to public goods","volume":"102","author":"Keser","year":"2000","journal-title":"Scand. J. Econ."},{"key":"2026010719422531100_B4","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1016\/S0165-1765(01)00394-9","article-title":"Are people conditionally cooperative? Evidence from a public goods experiment","volume":"71","author":"Fischbacher","year":"2001","journal-title":"Econ. Lett."},{"key":"2026010719422531100_B5","first-page":"891","article-title":"Cooperation in public-goods experiments: kindness or confusion","volume":"85","author":"Andreoni","year":"1995","journal-title":"Am. Econ. Rev."},{"key":"2026010719422531100_B6","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/415137a","article-title":"Altruistic punishment in humans","volume":"415","author":"Fehr","year":"2002","journal-title":"Nature"},{"key":"2026010719422531100_B7","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.physa.2014.06.040","article-title":"Social influence promotes cooperation in the public goods game","volume":"413","author":"Wu","year":"2014","journal-title":"Phys. A"},{"key":"2026010719422531100_B8","doi-asserted-by":"crossref","DOI":"10.1145\/3432945","article-title":"An ideal human: expectations of AI teammates in human-AI teaming","volume":"4","author":"Zhang","year":"2021","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"2026010719422531100_B9","doi-asserted-by":"crossref","first-page":"103174","DOI":"10.1016\/j.im.2019.103174","article-title":"Machines as teammates: a research agenda on AI in team collaboration","volume":"57","author":"Seeber","year":"2020","journal-title":"Inform. Manag."},{"key":"2026010719422531100_B10","doi-asserted-by":"crossref","first-page":"102145","DOI":"10.1016\/j.socec.2023.102145","article-title":"Cooperation is unaffected by the threat of severe adverse events in public goods games","volume":"108","author":"Bilancini","year":"2024","journal-title":"J. Behav. Exp. Econ."},{"key":"2026010719422531100_B11","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.euroecorev.2016.03.001","article-title":"Group size and the (in)efficiency of pure public good provision","volume":"85","author":"Diederich","year":"2016","journal-title":"Eur. Econ. Rev."},{"key":"2026010719422531100_B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0047-2727(94)90068-X","article-title":"Group size and the voluntary provision of public goods: experimental evidence utilizing large groups","volume":"54","author":"Isaac","year":"1994","journal-title":"J. Public Econ."},{"key":"2026010719422531100_B13","article-title":"Group size effects and critical mass in public goods games","volume":"9","author":"Pereda","year":"2019","journal-title":"Sci. Rep."},{"key":"2026010719422531100_B14","doi-asserted-by":"crossref","DOI":"10.1038\/srep07937","article-title":"Group size effect on cooperation in one-shot social dilemmas","volume":"5","author":"Barcelo","year":"2015","journal-title":"Sci. Rep."},{"key":"2026010719422531100_B15","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0131419","article-title":"Group size effect on cooperation in one-shot social dilemmas II: curvilinear effect","volume":"10","author":"Capraro","year":"2015","journal-title":"PLoS ONE"},{"key":"2026010719422531100_B16","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-50964-w","article-title":"Large scale and information effects on cooperation in public good games","volume":"9","author":"Pereda","year":"2019","journal-title":"Sci. Rep."},{"key":"2026010719422531100_B17","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.euroecorev.2019.05.019","article-title":"Public good provision by large groups \u2013 the logic of collective action revisited","volume":"118","author":"Weimann","year":"2019","journal-title":"Eur. Econ. Rev."},{"key":"2026010719422531100_B18","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1037\/a0023489","article-title":"Reward, punishment, and cooperation: a meta-analysis","volume":"137","author":"Balliet","year":"2011","journal-title":"Psychol. Bull."},{"key":"2026010719422531100_B19","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"2026010719422531100_B20","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"2026010719422531100_B21","doi-asserted-by":"crossref","first-page":"3449433","DOI":"10.1155\/2022\/3449433","article-title":"Improving the survival time of multiagents in social dilemmas through neurotransmitter-based deep Q-learning model of emotions","volume":"2022","author":"Hassan","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"2026010719422531100_B22","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1038\/s41562-018-0518-x","article-title":"Social learning strategies regulate the wisdom and madness of interactive crowds","volume":"3","author":"Toyokawa","year":"2019","journal-title":"Nat. Hum. Behav."},{"key":"2026010719422531100_B23","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1126\/science.aam6960","article-title":"DeepStack: expert-level artificial intelligence in heads-up no-limit poker","volume":"356","author":"Morav\u010d\u00edk","year":"2017","journal-title":"Science"},{"key":"2026010719422531100_B24","doi-asserted-by":"crossref","first-page":"72628","DOI":"10.1109\/ACCESS.2022.3189021","article-title":"Multiagent reinforcement learning for strategic decision making and control in robotic soccer through self-play","volume":"10","author":"Brandao","year":"2022","journal-title":"IEEE Access"},{"key":"2026010719422531100_B25","unstructured":"Capraro\n              V\n            \n          . 2023The impact of generative artificial intelligence on socioeconomic inequalities and policy making. arXiv (doi:arXiv:2401.05377)"},{"key":"2026010719422531100_B26","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2316205120","article-title":"The emergence of economic rationality of GPT","volume":"120","author":"Chen","year":"2023","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2026010719422531100_B27","doi-asserted-by":"crossref","unstructured":"Capraro\n              V\n            , Di PaoloR, PizziolV. 2023Predict-AI-bility of how humans balance self-interest with the interest of others. arXiv (doi:arXiv:2307.12776)","DOI":"10.2139\/ssrn.4517639"},{"key":"2026010719422531100_B28","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2313925121","article-title":"A Turing test of whether AI chatbots are behaviorally similar to humans","volume":"121","author":"Mei","year":"2024","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2026010719422531100_B29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18564\/jasss.3428","article-title":"The explanation of social conventions by melioration learning","volume":"20","author":"Zschache","year":"2017","journal-title":"J. Artif. Soc. Soc. Simul."},{"key":"2026010719422531100_B30","doi-asserted-by":"crossref","first-page":"7","DOI":"10.18564\/jasss.4771","article-title":"The role of reinforcement learning in the emergence of conventions: simulation experiments with the repeated volunteer\u2019s dilemma","volume":"25","author":"Nunner","journal-title":"J. Artif. Soc. Soc. Simul."},{"key":"2026010719422531100_B31","doi-asserted-by":"crossref","first-page":"533","DOI":"10.2307\/1911307","article-title":"The folk theorem in repeated games with discounting or with incomplete information","volume":"54","author":"Fudenberg","year":"1986","journal-title":"Econometrica"},{"key":"2026010719422531100_B32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/002200278002400101","article-title":"Effective choice in the prisoner\u2019s dilemma","volume":"24","author":"Axelrod","year":"1980","journal-title":"J. Conflict Resolut."},{"key":"2026010719422531100_B33","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"2026010719422531100_B34","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1023\/A:1026277420119","article-title":"Linear public goods experiments: a meta-analysis","volume":"6","author":"Zelmer","year":"2003","journal-title":"Exp. Econ."},{"key":"2026010719422531100_B35","unstructured":"RockinWool\n          . 2024Analysing_PGG_Using_RL. GitHub. Seehttps:\/\/github.com\/RockinWool\/Analysing_PGG_Using_RL."},{"key":"2026010719422531100_B36","article-title":"Data from: Analysing public goods games using reinforcement learning, effect of increasing group size on cooperation. Dryad Digital Repository","author":"Tamura","year":"2024"}],"container-title":["Royal Society Open Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsos.241195","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/doi\/full-xml\/10.1098\/rsos.241195","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article-pdf\/doi\/10.1098\/rsos.241195\/947919\/rsos.241195.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article-pdf\/doi\/10.1098\/rsos.241195\/947919\/rsos.241195.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:42:40Z","timestamp":1767832960000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/rsos\/article\/11\/12\/241195\/92449\/Analysing-public-goods-games-using-reinforcement"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":36,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1098\/rsos.241195","relation":{"has-review":[{"id-type":"doi","id":"10.1098\/RSOS.241195\/v4\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v3\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v4\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v3\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v3\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1098\/RSOS.241195\/v3\/decision1","asserted-by":"object"}]},"ISSN":["2054-5703"],"issn-type":[{"value":"2054-5703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"2024-06-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-10","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"241195"}}