{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T13:12:14Z","timestamp":1775135534566,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2017,7,1]],"date-time":"2017-07-01T00:00:00Z","timestamp":1498867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/tac.2016.2644871","type":"journal-article","created":{"date-parts":[[2016,12,24]],"date-time":"2016-12-24T14:38:42Z","timestamp":1482590322000},"page":"3323-3338","source":"Crossref","is-referenced-by-count":41,"title":["Sequential Decision Making With Coherent Risk"],"prefix":"10.1109","volume":"62","author":[{"given":"Aviv","family":"Tamar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7533-8300","authenticated-orcid":false,"given":"Yinlam","family":"Chow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Ghavamzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shie","family":"Mannor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/050638242"},{"key":"ref38","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1016\/S0927-0507(06)13019-4","article-title":"Gradient estimation","volume":"13","author":"fu","year":"2006","journal-title":"Simulation"},{"key":"ref32","article-title":"Tight approximations of dynamic risk measures","author":"iancu","year":"2011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00281-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-011-0367-0"},{"key":"ref37","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref36","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref35","author":"boyd","year":"2009","journal-title":"Convex optimization"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00296"},{"key":"ref28","article-title":"An approximate solution method for large risk-averse Markov decision processes","author":"petrik","year":"0","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9561","article-title":"Optimizing the CVaR via sampling","author":"tamar","year":"2015","journal-title":"AAAI"},{"key":"ref29","article-title":"A unifying framework for time-consistent, risk-averse model predictive control: Theory and algorithms","author":"chow","year":"0","journal-title":"Proc American Control Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref1","author":"markowitz","year":"1959","journal-title":"Portfolio Selection Efficient Diversification of Investment"},{"key":"ref20","article-title":"Scaling up robust MDPs using function approximation","author":"tamar","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref21","article-title":"Approximate dynamic programming for two-player zero-sum markov games","author":"perolat","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref24","article-title":"Policy gradients with variance related risk criteria","author":"tamar","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(01)00152-9"},{"key":"ref26","first-page":"3509","article-title":"Algorithms for CVaR optimization in MDPs","author":"chow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"252","article-title":"Actor-critic algorithms for risk-sensitive MDPs","author":"prashanth","year":"2013","journal-title":"Advances In Neural Information Processing Syst"},{"key":"ref50","article-title":"Risk-sensitive and robust decision-making: A CVaR optimization approach","author":"chow","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-02431-3","volume":"317","author":"rockafellar","year":"1998","journal-title":"Variational Analysis"},{"key":"ref52","author":"fiacco","year":"1983","journal-title":"Introduction to Sensitivity and Stability Analysis in Nonlinear Programming"},{"key":"ref10","article-title":"A multi-agent, policy-gradient approach to network routing","author":"tao","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics.","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref13","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control Volumes I and II"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/84537.84552"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1050.0186"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1120.0509"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref4","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control Vol I"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9965.00068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718751"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0393-3"},{"key":"ref8","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"JAIR"},{"key":"ref49","first-page":"233","article-title":"Robustness and risk-sensitivity in Markov decision processes","author":"osogami","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr.2014.6924109"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1515\/MCMA.2009.011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2001.041"},{"key":"ref42","first-page":"25","article-title":"Rules for ordering uncertain prospects","author":"hadar","year":"1969","journal-title":"The American Economic Review"},{"key":"ref41","first-page":"79","article-title":"Stable Paretian modeling in finance: Some empirical and theoretical aspects","author":"mittnik","year":"1998","journal-title":"A Practical Guide to Heavy Tails"},{"key":"ref44","author":"hull","year":"2006","journal-title":"Options Futures and Other Derivatives"},{"key":"ref43","first-page":"352","article-title":"Learning exercise policies for american options","volume":"5","author":"li","year":"0","journal-title":"Proc 12th Int Conf Artif Intell Stat JMLR W&CP"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/7956378\/07797146.pdf?arnumber=7797146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T22:18:18Z","timestamp":1658269098000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7797146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tac.2016.2644871","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7]]}}}