{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:34:08Z","timestamp":1780054448105,"version":"3.54.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319138220","type":"print"},{"value":"9783319138237","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-13823-7_31","type":"book-chapter","created":{"date-parts":[[2014,11,21]],"date-time":"2014-11-21T09:58:13Z","timestamp":1416563893000},"page":"357-375","source":"Crossref","is-referenced-by-count":44,"title":["Safe Exploration Techniques for Reinforcement Learning \u2013 An Overview"],"prefix":"10.1007","author":[{"given":"Martin","family":"Pecka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomas","family":"Svoboda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Coates, A., Quigley, M., Ng, A.Y.: An application of reinforcement learning to aerobatic helicopter flight. In: Proceedings of the 2006 Conference on Advances in Neural Information Processing Systems, vol.\u00a019, p. 1 (2007)","DOI":"10.7551\/mitpress\/7503.003.0006"},{"issue":"5","key":"31_CR2","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B.D. Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robotics and Autonomous Systems\u00a057(5), 469\u2013483 (2009)","journal-title":"Robotics and Autonomous Systems"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative search network: A reinforcement learning associative memory. Biological Cybernetics (1981)","DOI":"10.1007\/BF00453370"},{"key":"31_CR4","unstructured":"Bertsekas, D.P.: Dynamic programming: deterministic and stochastic models. Prentice-Hall (1987)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chernova, S., Veloso, M.: Confidence-based policy learning from demonstration using Gaussian mixture models. In: AAMAS 2007 Proceedings, p.\u00a01. ACM Press (2007)","DOI":"10.1145\/1329125.1329407"},{"key":"31_CR6","unstructured":"Consortium, N.: NIFTi robotic UGV platform (2010)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Coraluppi, S.P., Marcus, S.I.: Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes. Automatica (1999)","DOI":"10.1016\/S0005-1098(98)00153-8"},{"key":"31_CR8","first-page":"225","volume-title":"Proceedings of the 24th International Conference on Machine Learning, ICML 2007","author":"E. Delage","year":"2007","unstructured":"Delage, E., Mannor, S.: Percentile optimization in uncertain Markov decision processes with application to efficient exploration. In: Proceedings of the 24th International Conference on Machine Learning, ICML 2007, pp. 225\u2013232. ACM Press, New York (2007)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Ertle, P., Tokic, M., Cubek, R., Voos, H., Soffker, D.: Towards learning of safety knowledge from human demonstrations. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5394\u20135399. IEEE (October 2012)","DOI":"10.1109\/IROS.2012.6385714"},{"key":"31_CR10","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1613\/jair.3761","volume":"45","author":"J. Garcia","year":"2012","unstructured":"Garcia, J., Fern\u00e1ndez, F.: Safe exploration of state and action spaces in reinforcement learning. Journal of Artificial Intelligence Research\u00a045, 515\u2013564 (2012)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Garcia Polo, F.J., Rebollo, F.F.: Safe reinforcement learning in high-risk tasks through policy improvement. In: 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), pp. 76\u201383. IEEE (April 2011)","DOI":"10.1109\/ADPRL.2011.5967356"},{"key":"31_CR12","unstructured":"Geibel, P.: Reinforcement learning with bounded risk. In: ICML, pp. 162\u2013169 (2001)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Gillula, J.H., Tomlin, C.J.: Guaranteed safe online learning of a bounded system. In: 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 2979\u20132984. IEEE (September 2011)","DOI":"10.1109\/IROS.2011.6048864"},{"key":"31_CR14","unstructured":"Hans, A., Schneega\u00df, D., Sch\u00e4fer, A., Udluft, S.: Safe exploration for reinforcement learning. In: Proceedings of European Symposium on Artificial Neural Networks, pp. 23\u201325 (April 2008)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Heger, M.: Consideration of risk in reinforcement learning. In: 11th International Machine Learning Conference (1994)","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"key":"31_CR16","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. Technology Press of Massachusetts Institute of Technology (1960)"},{"key":"31_CR17","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"31_CR18","unstructured":"Kim, D., Kim, K.E., Poupart, P.: Cost-Sensitive Exploration in Bayesian Reinforcement Learning. In: Proceedings of Neural Information Processing Systems (NIPS) (2012)"},{"issue":"2-3","key":"31_CR19","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1023\/A:1017940631555","volume":"49","author":"O. Mihatsch","year":"2002","unstructured":"Mihatsch, O., Neuneier, R.: Risk-sensitive reinforcement learning. Machine Learning\u00a049(2-3), 267\u2013290 (2002)","journal-title":"Machine Learning"},{"key":"31_CR20","unstructured":"Moldovan, T.M., Abbeel, P.: Safe Exploration in Markov Decision Processes. In: Proceedings of the 29th International Conference on Machine Learning (May 2012)"},{"issue":"5","key":"31_CR21","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1287\/opre.1050.0216","volume":"53","author":"A. Nilim","year":"2005","unstructured":"Nilim, A., El Ghaoui, L.: Robust Control of Markov Decision Processes with Uncertain Transition Matrices. Operations Research\u00a053(5), 780\u2013798 (2005)","journal-title":"Operations Research"},{"key":"31_CR22","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1613\/jair.1666","volume":"24","author":"P. Geibel","year":"2011","unstructured":"Geibel, P., Wysotzki, F.: Risk-Sensitive Reinforcement Learning Applied to Control under Constraints. Journal Of Artificial Intelligence Research\u00a024, 81\u2013108 (2011)","journal-title":"Journal Of Artificial Intelligence Research"},{"key":"31_CR23","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. John Wiley & Sons, Inc., New York (1994)","edition":"1"},{"key":"31_CR24","first-page":"1047","volume":"9","author":"J.G. Schneider","year":"1996","unstructured":"Schneider, J.G.: Exploiting model uncertainty estimates for safe dynamic control learning. Neural Information Processing Systems\u00a09, 1047\u20131053 (1996)","journal-title":"Neural Information Processing Systems"},{"issue":"3-4","key":"31_CR25","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"C.J. Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Machine Learning\u00a08(3-4), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"31_CR26","unstructured":"Williams, R.J., Baird, L.C.: Tight performance bounds on greedy policies based on imperfect value functions. Tech. rep., Northeastern University,College of Computer Science (1993)"}],"container-title":["Lecture Notes in Computer Science","Modelling and Simulation for Autonomous Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-13823-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T11:00:39Z","timestamp":1689678039000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-13823-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319138220","9783319138237"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-13823-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}