{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T06:05:37Z","timestamp":1762409137217},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T00:00:00Z","timestamp":1443484800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Game Theory"],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1007\/s00182-015-0499-1","type":"journal-article","created":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T07:35:42Z","timestamp":1443512142000},"page":"985-1011","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Generalized reinforcement learning in perfect-information games"],"prefix":"10.1007","volume":"45","author":[{"given":"Maxwell","family":"Pak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,9,29]]},"reference":[{"key":"499_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jet.2004.03.008","volume":"122","author":"A Beggs","year":"2005","unstructured":"Beggs A (2005) On the convergence of reinforcement learning. J Econ Theory 122:1\u201336","journal-title":"J Econ Theory"},{"key":"499_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/jeth.1997.2319","volume":"77","author":"T Borgers","year":"1997","unstructured":"Borgers T, Sarin R (1997) Learning through reinforcement and replicator dynamics. J Econ Theory 77:1\u201314","journal-title":"J Econ Theory"},{"key":"499_CR3","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511779398","volume-title":"Probability: theory and examples","author":"R Durrett","year":"2010","unstructured":"Durrett R (2010) Probability: theory and examples, 4th edn. Duxbury Press, New York","edition":"4"},{"key":"499_CR4","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.2307\/2951493","volume":"61","author":"G Ellison","year":"1993","unstructured":"Ellison G (1993) Learning, local interaction, and coordination. Econometrica 61:1047\u20131072","journal-title":"Econometrica"},{"key":"499_CR5","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1111\/1468-0262.00372","volume":"70","author":"E Hopkins","year":"2002","unstructured":"Hopkins E (2002) Two competing models of how people learn in games. Econometrica 70:2141\u20132166","journal-title":"Econometrica"},{"key":"499_CR6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jet.2004.09.004","volume":"124","author":"P Jehiel","year":"2000","unstructured":"Jehiel P, Samet D (2000) Learning to play games in extensive form by valuation. J Econ Theory 124:129\u2013148","journal-title":"J Econ Theory"},{"key":"499_CR7","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s001820400194","volume":"33","author":"J-F Laslier","year":"2005","unstructured":"Laslier J-F, Walliser B (2005) A reinforcement learning process in extensive form games. Int J Game Theory 33:219\u2013227","journal-title":"Int J Game Theory"},{"key":"499_CR8","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1006\/game.2000.0841","volume":"37","author":"J-F Laslier","year":"2001","unstructured":"Laslier J-F, Topol R, Walliser B (2001) A behavioral learning process in games. Games Econ Behav 37:340\u2013366","journal-title":"Games Econ Behav"},{"key":"499_CR9","volume-title":"Probability theory","author":"M Lo\u00e8ve","year":"1978","unstructured":"Lo\u00e8ve M (1978) Probability theory, vol II, 4th edn. Springer, Berlin","edition":"4"},{"key":"499_CR10","doi-asserted-by":"crossref","unstructured":"Marx L, Swinkels J (1997) Order independence for iterated weak dominance. Games Econ Behav 18:219\u2013245","DOI":"10.1006\/game.1997.0525"},{"key":"499_CR11","volume-title":"A course in game theory","author":"M Osborne","year":"1994","unstructured":"Osborne M, Rubinstein A (1994) A course in game theory. MIT Press, Cambridge"},{"key":"499_CR12","doi-asserted-by":"crossref","unstructured":"\u00d8sterdal L (2005) Iterated weak dominance and subgame dominance.J Math Econ 41:637\u2013645","DOI":"10.1016\/j.jmateco.2003.11.013"},{"key":"499_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/07-PS094","volume":"4","author":"R Pemantle","year":"2007","unstructured":"Pemantle R (2007) A survey of random processes with reinforcement. Probab Surv 4:1\u201379","journal-title":"Probab Surv"},{"key":"499_CR14","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1006\/game.1998.0702","volume":"28","author":"R Sarin","year":"1999","unstructured":"Sarin R, Vahid F (1999) Payoff assessments without probabilities: a simple dynamic model of choice. Games Econ Behav 28:294\u2013309","journal-title":"Games Econ Behav"}],"container-title":["International Journal of Game Theory"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00182-015-0499-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00182-015-0499-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00182-015-0499-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00182-015-0499-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,23]],"date-time":"2019-05-23T18:40:54Z","timestamp":1558636854000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00182-015-0499-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,29]]},"references-count":14,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,11]]}},"alternative-id":["499"],"URL":"https:\/\/doi.org\/10.1007\/s00182-015-0499-1","relation":{},"ISSN":["0020-7276","1432-1270"],"issn-type":[{"value":"0020-7276","type":"print"},{"value":"1432-1270","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9,29]]}}}