{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T17:26:30Z","timestamp":1725989190314},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030001100"},{"type":"electronic","value":"9783030001117"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-00111-7_20","type":"book-chapter","created":{"date-parts":[[2018,8,30]],"date-time":"2018-08-30T00:32:07Z","timestamp":1535589127000},"page":"229-240","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Risk-Sensitivity in Simulation Based Online Planning"],"prefix":"10.1007","author":[{"given":"Kyrill","family":"Schmid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lenz","family":"Belzner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie","family":"Kiermeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Neitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomy","family":"Phan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Gabor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Linnhoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,30]]},"reference":[{"key":"20_CR1","unstructured":"Galichet, N., Sebag, M., Teytaud, O.: Exploration vs exploitation vs safety: risk-aware multi-armed bandits. In: ACML, pp. 245\u2013260 (2013)"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Heger, M.: Consideration of risk in reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 105\u2013111 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"issue":"7","key":"20_CR3","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1287\/mnsc.18.7.356","volume":"18","author":"RA Howard","year":"1972","unstructured":"Howard, R.A., Matheson, J.E.: Risk-sensitive Markov decision processes. Manag. Sci. 18(7), 356\u2013369 (1972)","journal-title":"Manag. Sci."},{"key":"20_CR4","unstructured":"Kisiala, J.: Conditional value-at-risk: theory and applications. arXiv preprint arXiv:1511.00140 (2015)"},{"key":"20_CR5","unstructured":"Moldovan, T.M.: Safety, risk awareness and exploration in reinforcement learning. Ph.D. thesis, University of California, Berkeley (2014)"},{"issue":"1","key":"20_CR6","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"20_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-28934-2_1","volume-title":"Formal Aspects of Component Software","author":"L Belzner","year":"2016","unstructured":"Belzner, L., Hennicker, R., Wirsing, M.: OnPlan: a framework for simulation-based online planning. In: Braga, C., \u00d6lveczky, P.C. (eds.) FACS 2015. LNCS, vol. 9539, pp. 1\u201330. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28934-2_1"},{"key":"20_CR8","volume-title":"Dynamic Programming and Markov Processes","author":"RA Howard","year":"1964","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. Wiley for The Massachusetts Institute of Technology, New York (1964)"},{"key":"20_CR9","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"key":"20_CR10","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)"},{"key":"20_CR11","unstructured":"Weinstein, A.: Local planning for continuous Markov decision processes. Rutgers The State University of New Jersey-New Brunswick (2014)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Weinstein, A., Littman, M.L.: Open-loop planning in large-scale stochastic domains. In: AAAI (2013)","DOI":"10.1609\/aaai.v27i1.8547"},{"key":"20_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based monte-carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"issue":"1","key":"20_CR14","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT Boer De","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134(1), 19\u201367 (2005)","journal-title":"Ann. Oper. Res."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Belzner, L.: Time-adaptive cross entropy planning. In: Proceedings of the 31st Annual ACM Symposium on Applied Computing, pp. 254\u2013259. ACM (2016)","DOI":"10.1145\/2851613.2851704"},{"key":"20_CR16","unstructured":"Liu, Y.: Decision-theoretic planning under risk-sensitive planning objectives. Ph.D. thesis, Georgia Institute of Technology (2005)"},{"issue":"3\u20134","key":"20_CR17","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"1","key":"20_CR18","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1137\/0325004","volume":"25","author":"KJ Chung","year":"1987","unstructured":"Chung, K.J., Sobel, M.J.: Discounted MDP\u2019s: distribution functions and exponential utility maximization. SIAM J. Control Optim. 25(1), 49\u201362 (1987)","journal-title":"SIAM J. Control Optim."},{"key":"20_CR19","unstructured":"Moldovan, T.M., Abbeel, P.: Risk aversion in Markov decision processes via near optimal Chernoff bounds. In: NIPS, pp. 3140\u20133148 (2012)"},{"issue":"12","key":"20_CR20","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1093\/ietisy\/e90-d.12.2043","volume":"90","author":"H Kashima","year":"2007","unstructured":"Kashima, H.: Risk-sensitive learning via minimization of empirical conditional value-at-risk. IEICE Trans. Inf. Syst. 90(12), 2043\u20132052 (2007)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"20_CR21","doi-asserted-by":"publisher","first-page":"21","DOI":"10.21314\/JOR.2000.038","volume":"2","author":"RT Rockafellar","year":"2000","unstructured":"Rockafellar, R.T., Uryasev, S., et al.: Optimization of conditional value-at-risk. J. Risk 2, 21\u201342 (2000)","journal-title":"J. Risk"},{"issue":"1","key":"20_CR22","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1093\/jjfinec\/nbm019","volume":"6","author":"SX Chen","year":"2008","unstructured":"Chen, S.X.: Nonparametric estimation of expected shortfall. J. Financ. Econom. 6(1), 87\u2013107 (2008)","journal-title":"J. Financ. Econom."}],"container-title":["Lecture Notes in Computer Science","KI 2018: Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00111-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T17:34:41Z","timestamp":1661880881000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-00111-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030001100","9783030001117"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00111-7_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}