{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:47:02Z","timestamp":1768312022488,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312619","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"5899-5904","source":"Crossref","is-referenced-by-count":0,"title":["Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics"],"prefix":"10.1109","author":[{"given":"Yizhou","family":"Zhang","sequence":"first","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Mazumdar","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Department of Computing and Mathematical Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Tractable equilibrium computation in markov games through risk aversion","author":"Mazumdar","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/2951567"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/game.1995.1023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0899-8256(03)00052-6"},{"issue":"4","key":"ref5","first-page":"848","article-title":"Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria","volume":"88","author":"Erev","year":"1998","journal-title":"American Economic Review"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2483699.2483703"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975031.172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/18M1231298"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2307\/1911749"},{"key":"ref10","first-page":"3507","article-title":"Doubly optimal no-regret learning in monotone games","volume-title":"International Conference on Machine Learning","author":"Cai"},{"key":"ref11","first-page":"20766","article-title":"Tight last-iterate convergence rates for no-regret learning in multi-player games","volume":"33","author":"Golowich","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"The complexity of markov equilibrium in stochastic games","author":"Daskalakis","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s007800200072"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0778"},{"key":"ref15","article-title":"A unified approach to reinforcement learning, quantal response equilibria, and two-player zero-sum games","author":"Sokota","year":"2023"},{"key":"ref16","article-title":"Soft robust mdps and risk-sensitive mdps: Equivalence, policy gradient, and sample complexity","author":"Zhang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2012.0683"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11238-023-09941-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02431-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312619.pdf?arnumber=11312619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:32:36Z","timestamp":1768293156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312619","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}