{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:18:56Z","timestamp":1770337136240,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72342006"],"award-info":[{"award-number":["72342006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discrete Event Dyn Syst"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s10626-026-00423-2","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:28:54Z","timestamp":1770290934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Team variance optimization of n-player stochastic games with separately controlled chains"],"prefix":"10.1007","volume":"36","author":[{"given":"Li","family":"Xia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"issue":"3","key":"423_CR1","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s00186-011-0367-0","volume":"74","author":"N B\u00e4uerle","year":"2011","unstructured":"B\u00e4uerle N, Ott J (2011) Markov decision processes with average-value-at-risk criteria. Math Methods Oper Res 74(3):361\u2013379","journal-title":"Math Methods Oper Res"},{"key":"423_CR2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/14207.001.0001","volume-title":"Distributional Reinforcement Learning","author":"MG Bellemare","year":"2023","unstructured":"Bellemare MG, Dabney W, Rowland M (2023) Distributional Reinforcement Learning. MIT Press"},{"key":"423_CR3","doi-asserted-by":"crossref","unstructured":"Bisi L, Sabbioni L, Vittori E, Papini M, Restelli M (2020) Risk-averse trust region optimization for reward-volatility reduction. Proceed 29th Int Joint Conf Artif Intell (IJCAI\u201920), 4583-4589","DOI":"10.24963\/ijcai.2020\/632"},{"key":"423_CR4","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/s10626-024-00405-2","volume":"34","author":"R Blancas-Rivera","year":"2024","unstructured":"Blancas-Rivera R, Jasso-Fuentes H (2024) Discrete-time hybrid control with risk-sensitive discounted costs. Disc Event Dyna Syst 34:659\u2013687","journal-title":"Disc Event Dyna Syst"},{"issue":"2","key":"423_CR5","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3934\/jdg.2023024","volume":"11","author":"VS Borkar","year":"2024","unstructured":"Borkar VS (2024) Risk-sensitive control, single controller games and linear programming. J Dyna Games 11(2):150\u2013159","journal-title":"J Dyna Games"},{"issue":"1","key":"423_CR6","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1287\/moor.27.1.192.334","volume":"27","author":"VS Borkar","year":"2002","unstructured":"Borkar VS, Meyn SP (2002) Risk-sensitive optimal control for Markov decision processes with monotone cost. Math Oper Res 27(1):192\u2013209","journal-title":"Math Oper Res"},{"key":"423_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-69082-7","volume-title":"Stochastic Learning and Optimization - A Sensitivity-Based Approach","author":"XR Cao","year":"2007","unstructured":"Cao XR (2007) Stochastic Learning and Optimization - A Sensitivity-Based Approach. Springer, New York"},{"issue":"3","key":"423_CR8","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s10626-023-00376-w","volume":"33","author":"R Cavazos-Cadena","year":"2023","unstructured":"Cavazos-Cadena R, Cruz-Su\u00e1rez H, Montes-De-Oca R (2023) Average criteria in denumerable semi-Markov decision chains under risk-aversion. Disc Event Dyna Syst 33(3):221\u2013256","journal-title":"Disc Event Dyna Syst"},{"key":"423_CR9","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1287\/opre.42.1.184","volume":"42","author":"KJ Chung","year":"1994","unstructured":"Chung KJ (1994) Mean-variance tradeoffs in an undiscounted MDP: The unichain case. Oper Res 42:184\u2013188","journal-title":"Oper Res"},{"key":"423_CR10","doi-asserted-by":"crossref","unstructured":"Escobedo-Trujillo BA, L\u00f3pez-Barrientos JD, Colorado-Garrido D, Alaffita-Hern\u00e1ndez FA (2024) Variance optimality in constrained and unconstrained stochastic differential games. Results Control Optimiz 14:100354","DOI":"10.1016\/j.rico.2023.100354"},{"issue":"2","key":"423_CR11","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1137\/22M1512880","volume":"62","author":"SR Etesami","year":"2024","unstructured":"Etesami SR (2024) Learning stationary Nash equilibrium policies in $$n$$-player stochastic games with independent chains. SIAM J Control Optim 62(2):799\u2013825","journal-title":"SIAM J Control Optim"},{"issue":"2018","key":"423_CR12","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.1109\/TAC.2018.2797217","volume":"63","author":"SR Etesami","year":"2018","unstructured":"Etesami SR, Saad W, Mandayam NB, Poor HV (2018) Stochastic games for the smart grid energy management with prospect prosumers. IEEE Trans Autom Control 63(2018):2327\u20132342","journal-title":"IEEE Trans Autom Control"},{"issue":"1","key":"423_CR13","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1287\/moor.14.1.147","volume":"14","author":"JA Filar","year":"1989","unstructured":"Filar JA, Kallenberg LCM, Lee HM (1989) Variance-penalized Markov decision processes. Math Oper Res 14(1):147\u2013161","journal-title":"Math Oper Res"},{"key":"423_CR14","volume-title":"Statistical Methods for Research Workers","author":"RA Fisher","year":"1925","unstructured":"Fisher RA (1925) Statistical Methods for Research Workers. Oliver & Boyd, Edinburgh"},{"key":"423_CR15","doi-asserted-by":"publisher","first-page":"2151","DOI":"10.1109\/TAC.2009.2023833","volume":"54","author":"X Guo","year":"2009","unstructured":"Guo X, Song XY (2009) Mean-variance criteria for finite continuous-time Markov decision processes. IEEE Trans Autom Control 54:2151\u20132157","journal-title":"IEEE Trans Autom Control"},{"key":"423_CR16","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1137\/S0363012998340673","volume":"38","author":"O Hern\u00e1ndez-Lerma","year":"1999","unstructured":"Hern\u00e1ndez-Lerma O, Vega-Amaya O, Carrasco G (1999) Sample-path optimality and variance-minimization of average cost Markov control processes. SIAM J Control Optim 38:79\u201393","journal-title":"SIAM J Control Optim"},{"issue":"7","key":"423_CR17","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1287\/mnsc.18.7.356","volume":"18","author":"RA Howard","year":"1972","unstructured":"Howard RA, Matheson JE (1972) Risk-sensitive Markov decision processes. Manage Sci 18(7):356\u2013369","journal-title":"Manage Sci"},{"issue":"4","key":"423_CR18","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s10626-018-0273-1","volume":"28","author":"Y Huang","year":"2018","unstructured":"Huang Y (2018) Finite horizon continuous-time Markov decision processes with mean and variance criteria. Disc Event Dyna Syst Theory Appl 28(4):539\u2013564","journal-title":"Disc Event Dyna Syst Theory Appl"},{"issue":"3","key":"423_CR19","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1111\/1467-9965.00100","volume":"10","author":"D Li","year":"2000","unstructured":"Li D, Ng WL (2000) Optimal dynamic portfolio selection: Multiperiod mean-variance formulation. Math Financ 10(3):387\u2013406","journal-title":"Math Financ"},{"key":"423_CR20","doi-asserted-by":"crossref","unstructured":"Li, D. and Young, V. R. (2022). Stackelberg differential game for reinsurance: Mean-variance framework and random horizon. Insurance: Math Econ 102:42-55","DOI":"10.1016\/j.insmatheco.2021.11.006"},{"issue":"3","key":"423_CR21","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1287\/opre.2021.2123","volume":"70","author":"X Li","year":"2022","unstructured":"Li X, Zhong H, Brandeau ML (2022) Quantile Markov decision processes. Oper Res 70(3):1428\u20131447","journal-title":"Oper Res"},{"key":"423_CR22","doi-asserted-by":"publisher","first-page":"230","DOI":"10.3390\/math9030230","volume":"9","author":"E Parilina","year":"2021","unstructured":"Parilina E, Akimochkin S (2021) Cooperative stochastic games with mean-variance preferences. Mathematics 9:230","journal-title":"Mathematics"},{"key":"423_CR23","unstructured":"Prashanth, L. A. and Ghavamzadeh, M. (2013). Actor-critic algorithms for risk-sensitive MDPs. Adv Neural Inf Process Syst (NIPS\u20192013), 252-260"},{"key":"423_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"1994","unstructured":"Puterman ML (1994) Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, New York"},{"issue":"2","key":"423_CR25","doi-asserted-by":"publisher","first-page":"27E","DOI":"10.1179\/jmt.2009.17.2.27E","volume":"17","author":"SF Sawyer","year":"2009","unstructured":"Sawyer SF (2009) Analysis of variance: The fundamental concepts. J Manual Manipul Therapy 17(2):27E-38E","journal-title":"J Manual Manipul Therapy"},{"issue":"4","key":"423_CR26","doi-asserted-by":"publisher","first-page":"794","DOI":"10.2307\/3213832","volume":"19","author":"MJ Sobel","year":"1982","unstructured":"Sobel MJ (1982) The variance of discounted Markov decision processes. J Appl Probab 19(4):794\u2013802","journal-title":"J Appl Probab"},{"key":"423_CR27","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1287\/opre.42.1.175","volume":"42","author":"MJ Sobel","year":"1994","unstructured":"Sobel MJ (1994) Mean-variance tradeoffs in an undiscounted MDP. Oper Res 42:175\u2013183","journal-title":"Oper Res"},{"key":"423_CR28","unstructured":"Tamar A, Castro D D, Mannor S (2012) Policy gradients with variance related risk criteria. Proceed 29th Int Conf Mach Learn (ICML\u20192012), Edinburgh, Scotland"},{"key":"423_CR29","doi-asserted-by":"crossref","unstructured":"Wen X, Guo X, Xia L (2024) Finite horizon partially observable semi-Markov decision processes under risk probability criteria. Oper Res Lett 57:107187","DOI":"10.1016\/j.orl.2024.107187"},{"key":"423_CR30","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/BF01720350","volume":"14","author":"DJ White","year":"1992","unstructured":"White DJ (1992) Computational approaches to variance-penalized Markov decision processes. OR-Spektrum 14:79\u201383","journal-title":"OR-Spektrum"},{"issue":"2","key":"423_CR31","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1006\/jmaa.1993.1093","volume":"173","author":"DJ White","year":"1993","unstructured":"White DJ (1993) Minimizing a threshold probability in discounted Markov decision processes. J Math Anal Appl 173(2):634\u2013646","journal-title":"J Math Anal Appl"},{"issue":"3","key":"423_CR32","doi-asserted-by":"publisher","first-page":"249","DOI":"10.3934\/jdg.2023025","volume":"11","author":"Y Wu","year":"2024","unstructured":"Wu Y, Zhang J (2024) The relationships between discounted and average criteria of stochastic games with prospect theory. J Dyna Games 11(3):249\u2013264","journal-title":"J Dyna Games"},{"key":"423_CR33","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.automatica.2017.11.012","volume":"88","author":"L Xia","year":"2018","unstructured":"Xia L (2018) Mean-variance optimization of discrete time discounted Markov decision processes. Automatica 88:76\u201382","journal-title":"Automatica"},{"issue":"12","key":"423_CR34","doi-asserted-by":"publisher","first-page":"2808","DOI":"10.1111\/poms.13252","volume":"29","author":"L Xia","year":"2020","unstructured":"Xia L (2020) Risk-sensitive Markov decision processes with combined metrics of mean and variance. Prod Oper Manag 29(12):2808\u20132827","journal-title":"Prod Oper Manag"},{"issue":"12","key":"423_CR35","doi-asserted-by":"publisher","first-page":"4049","DOI":"10.1111\/poms.14077","volume":"32","author":"L Xia","year":"2023","unstructured":"Xia L, Zhang L, Glynn PW (2023) Risk-sensitive Markov decision processes with long-run cvar criterion. Prod Oper Manag 32(12):4049\u20134067","journal-title":"Prod Oper Manag"},{"issue":"6","key":"423_CR36","first-page":"2430","volume":"72","author":"Y Yan","year":"2024","unstructured":"Yan Y, Li G, Chen Y, Fan J (2024) Model-based reinforcement learning for offline zero-sum Markov games. Manage Sci 72(6):2430\u20132445","journal-title":"Manage Sci"},{"issue":"10","key":"423_CR37","doi-asserted-by":"publisher","first-page":"5230","DOI":"10.1109\/TAC.2021.3121228","volume":"67","author":"B Yongacoglu","year":"2021","unstructured":"Yongacoglu B, Arslan G, Y\u00fcksel S (2021) Decentralized learning for optimality in stochastic dynamic teams and games with local control and global state information. IEEE Trans Autom Control 67(10):5230\u20135245","journal-title":"IEEE Trans Autom Control"},{"key":"423_CR38","doi-asserted-by":"crossref","unstructured":"Zhang K, Yang Z, Ba\u015far T (2021) Multi-agent reinforcement learning: A selective overview of theories and algorithms. Vamvoudakis KG, Wan Y, Lewis FL, Cansever D, eds. Handbook of Reinforcement Learning and Control (Springer, Cham), 321-384","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"423_CR39","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s002450010003","volume":"42","author":"XY Zhou","year":"2000","unstructured":"Zhou XY, Li D (2000) Continuous-time mean-variance portfolio selection: A stochastic LQ framework. Appl Math Optimiz 42:19\u201333","journal-title":"Appl Math Optimiz"},{"key":"423_CR40","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1137\/S0363012902405583","volume":"42","author":"XY Zhou","year":"2004","unstructured":"Zhou XY, Yin G (2004) Markowitz\u2019s mean-variance portfolio selection with regime switching: A continuous-time model. SIAM J Control Optim 42:1466\u20131482","journal-title":"SIAM J Control Optim"}],"container-title":["Discrete Event Dynamic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10626-026-00423-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10626-026-00423-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10626-026-00423-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:28:56Z","timestamp":1770290936000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10626-026-00423-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["423"],"URL":"https:\/\/doi.org\/10.1007\/s10626-026-00423-2","relation":{},"ISSN":["0924-6703","1573-7594"],"issn-type":[{"value":"0924-6703","type":"print"},{"value":"1573-7594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"assertion":[{"value":"13 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"7"}}