{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:39:08Z","timestamp":1787499548977,"version":"build-2736575974"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967699","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1101-1106","source":"Crossref","is-referenced-by-count":14,"title":["Entropic Risk Measure in Policy Search"],"prefix":"10.1109","author":[{"given":"David","family":"Nass","sequence":"first","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems Lab,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Belousov","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems Lab,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems Lab,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1973.1100265"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(90)90110-G"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0113240"},{"key":"ref14","first-page":"1651","article-title":"Policy gradients with variance related risk criteria","author":"tamar","year":"2012","journal-title":"ICML"},{"key":"ref15","first-page":"155","article-title":"Policy gradients for cvar-constrained mdps","author":"prashanth","year":"2014","journal-title":"ALT"},{"key":"ref16","author":"tamar","year":"2015","journal-title":"Risk-sensitive and efficient reinforcement learning algorithms"},{"key":"ref17","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/S1365100502027025"},{"key":"ref19","first-page":"764","volume":"13","year":"1981","journal-title":"Risk-sensitive linear\/quadratic\/gaussian control"},{"key":"ref28","first-page":"2616","article-title":"Probabilistic movement primitives","author":"paraschos","year":"2013","journal-title":"NIPS"},{"key":"ref4","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1561\/2400000023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref29","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"NIPS"},{"key":"ref5","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1142\/S0219493711003334"},{"key":"ref1","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9290-3"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref21","first-page":"1","article-title":"Graphical models, exponential families, and variational inference","volume":"1","author":"wainwright","year":"2008","journal-title":"Foundations and Trends R in Machine Learning"},{"key":"ref24","first-page":"817","article-title":"Variational inference for policy search in changing situations","author":"neumann","year":"2011","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2008.4631255"},{"key":"ref26","article-title":"Maximum a posteriori policy optimisation","author":"abdolmaleki","year":"2018","journal-title":"arXiv preprint arXiv 1806 06920"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071252"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967699.pdf?arnumber=8967699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:39:42Z","timestamp":1753731582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967699","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}