{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T02:21:00Z","timestamp":1725848460345},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319289335"},{"type":"electronic","value":"9783319289342"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-28934-2_1","type":"book-chapter","created":{"date-parts":[[2016,1,28]],"date-time":"2016-01-28T15:32:56Z","timestamp":1453995176000},"page":"1-30","source":"Crossref","is-referenced-by-count":6,"title":["OnPlan: A Framework for Simulation-Based Online Planning"],"prefix":"10.1007","author":[{"given":"Lenz","family":"Belzner","sequence":"first","affiliation":[]},{"given":"Rolf","family":"Hennicker","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Wirsing","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,29]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Kolobov, A., Dai, P., Mausam, M., Weld, D.S.: Reverse iterative deepening for finite-horizon MDPS with large branching factors. In: Proceedings of the 22nd International Conference on Automated Planning and Scheduling, ICAPS (2012)","DOI":"10.1609\/icaps.v22i1.13523"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Keller, T., Helmert, M.: Trial-based Heuristic Tree Search for Finite Horizon MDPs. In: Proceedings of the 23rd International Conference on Automated Planning and Scheduling (ICAPS 2013), pp. 135\u2013143. AAAI Press, June 2013","DOI":"10.1609\/icaps.v23i1.13557"},{"key":"1_CR3","unstructured":"Weinstein, A.: Local Planning for Continuous Markov Decision Processes. Ph.D. thesis, Rutgers, The State University of New Jersey (2014)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Kephart, J.: An architectural blueprint for autonomic computing. IBM (2003)","DOI":"10.1109\/MC.2003.1160055"},{"issue":"1","key":"1_CR5","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1093\/biomet\/57.1.97","volume":"57","author":"WK Hastings","year":"1970","unstructured":"Hastings, W.K.: Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57(1), 97\u2013109 (1970)","journal-title":"Biometrika"},{"key":"1_CR6","volume-title":"Simulation and the Monte Carlo Method","author":"RY Rubinstein","year":"2011","unstructured":"Rubinstein, R.Y., Kroese, D.P.: Simulation and the Monte Carlo Method, vol. 707. Wiley, New York (2011)"},{"key":"1_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118612323.ch2","volume-title":"The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning","author":"RY Rubinstein","year":"2013","unstructured":"Rubinstein, R.Y., Kroese, D.P.: The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning. Springer Science & Business Media, New York (2013)"},{"issue":"19","key":"1_CR8","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1016\/j.tcs.2009.01.016","volume":"410","author":"JY Audibert","year":"2009","unstructured":"Audibert, J.Y., Munos, R., Szepesv\u00e1ri, C.: Exploration-exploitation tradeoff using variance estimates in multi-armed bandits. Theor. Comput. Sci. 410(19), 1876\u20131902 (2009)","journal-title":"Theor. Comput. Sci."},{"issue":"1","key":"1_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C.B., Powley, E., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A survey of monte carlo tree search methods. IEEE Trans. Comput. Intell. AI Game 4(1), 1\u201343 (2012)","journal-title":"IEEE Trans. Comput. Intell. AI Game"},{"key":"1_CR10","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)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Weinstein, A., Littman, M.L.: Open-loop planning in large-scale stochastic domains. In: Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence (2013)","DOI":"10.1609\/aaai.v27i1.8547"},{"issue":"3","key":"1_CR12","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1145\/2093548.2093574","volume":"55","author":"S Gelly","year":"2012","unstructured":"Gelly, S., Kocsis, L., Schoenauer, M., Sebag, M., Silver, D., Szepesv\u00e1ri, C., Teytaud, O.: The grand challenge of computer go: Monte carlo tree search and extensions. Commun. ACM 55(3), 106\u2013113 (2012)","journal-title":"Commun. ACM"},{"key":"1_CR13","unstructured":"Silver, D., Sutton, R.S., M\u00fcller, M.: Temporal-difference search in computer go. In: Borrajo, D., Kambhampati, S., Oddi, A., Fratini, S. (eds.) Proceedings of the Twenty-Third International Conference on Automated Planning and Scheduling, ICAPS 2013, Rome, Italy, June 10\u201314, 2013. AAAI (2013)"},{"issue":"11","key":"1_CR14","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1016\/j.artint.2011.03.007","volume":"175","author":"S Gelly","year":"2011","unstructured":"Gelly, S., Silver, D.: Monte-carlo tree search and rapid action value estimation in computer go. Artif. Intell. 175(11), 1856\u20131875 (2011)","journal-title":"Artif. Intell."},{"issue":"1","key":"1_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000024","volume":"5","author":"S Bubeck","year":"2012","unstructured":"Bubeck, S., Cesa-Bianchi, N.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5(1), 1\u2013122 (2012)","journal-title":"Found. Trends Mach. Learn."},{"issue":"2\u20133","key":"1_CR16","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"1_CR17","unstructured":"Sebastio, S., Vandin, A.: Multivesta: Statistical model checking for discrete event simulators. In: Proceedings of the 7th International Conference on Performance Evaluation Methodologies and Tools, ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), pp. 310\u2013315 (2013)"},{"issue":"1","key":"1_CR18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"P Boer de","year":"2005","unstructured":"de Boer, P., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Annals OR 134(1), 19\u201367 (2005)","journal-title":"Annals OR"},{"issue":"1","key":"1_CR19","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s10479-005-5731-0","volume":"134","author":"L Margolin","year":"2005","unstructured":"Margolin, L.: On the convergence of the cross-entropy method. Ann. Oper. Res. 134(1), 201\u2013214 (2005)","journal-title":"Ann. Oper. Res."},{"issue":"7","key":"1_CR20","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1177\/0278364912444543","volume":"31","author":"M Kobilarov","year":"2012","unstructured":"Kobilarov, M.: Cross-entropy motion planning. I. J. Robotic Res. 31(7), 855\u2013871 (2012)","journal-title":"I. J. Robotic Res."},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Livingston, S.C., Wolff, E.M., Murray, R.M.: Cross-entropy temporal logic motion planning. In: Proceedings of the 18th International Conference on Hybrid Systems: Computation and Control, HSCC 2015, pp. 269\u2013278 (2015)","DOI":"10.1145\/2728606.2728635"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1214\/aoms\/1177706645","volume":"29","author":"GE Box","year":"1958","unstructured":"Box, G.E., Muller, M.E.: A note on the generation of random normal deviates. Ann. Math. Stat. 29, 610\u2013611 (1958)","journal-title":"Ann. Math. Stat."},{"issue":"3","key":"1_CR23","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s10994-012-5322-7","volume":"90","author":"T Hester","year":"2013","unstructured":"Hester, T., Stone, P.: Texplore: real-time sample-efficient reinforcement learning for robots. Mach. Learn. 90(3), 385\u2013429 (2013)","journal-title":"Mach. Learn."},{"key":"1_CR24","unstructured":"Bonet, B., Geffner, H.: Labeled RTDP: Improving the convergence of real-time dynamic programming. In: ICAPS, vol. 3, pp. 12\u201321 (2003)"},{"key":"1_CR25","unstructured":"Karnin, Z., Koren, T., Somekh, O.: Almost optimal exploration in multi-armed bandits. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 1238\u20131246 (2013)"},{"key":"1_CR26","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-14923-3","volume-title":"Computer games","author":"T Cazenave","year":"2014","unstructured":"Cazenave, T., Pepels, T., Winands, M.H.M., Lanctot, M.: Minimizing\u00a0simple\u00a0and\u00a0cumulative\u00a0regret in\u00a0monte-carlo\u00a0tree\u00a0search. In: Cazenave, T., Winands, M.H.M., Bj\u00f6rnsson, Y. (eds.) CGW 2014. CCIS, vol. 504, pp. 1\u201315. Springer, Heidelberg (2014)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Mansley, C.R., Weinstein, A., Littman, M.L.: Sample-based planning for continuous action markov decision processes. In: Proceedings of the 21st International Conference on Automated Planning and Scheduling, ICAPS (2011)","DOI":"10.1609\/icaps.v21i1.13484"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Weinstein, A., Littman, M.L.: Bandit-based planning and learning in continuous-action markov decision processes. In: Proceedings of the 22nd International Conference on Automated Planning and Scheduling, ICAPS (2012)","DOI":"10.1609\/icaps.v22i1.13507"},{"key":"1_CR29","volume-title":"Principles of Model Checking","author":"C Baier","year":"2008","unstructured":"Baier, C., Katoen, J.P., et al.: Principles of Model Checking, vol. 26202649. MIT Press, Cambridge (2008)"},{"key":"1_CR30","series-title":"Lecture Notes in Computer Science","volume-title":"Software Engineering for Collective Autonomic Systems: Results of the ASCENS Project","year":"2015","unstructured":"Wirsing, M., H\u00f6lzl, M., Koch, N., Mayer, P. (eds.): Software Engineering for Collective Autonomic Systems: Results of the ASCENS Project. LNCS, vol. 8998. Springer, Heidelberg (2015)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"H\u00f6lzl, M.M., Gabor, T.: Continuous collaboration: A case study on the development of an adaptive cyber-physical system. In: 1st IEEE\/ACM International Workshop on Software Engineering for Smart Cyber-Physical Systems, SEsCPS 2015, pp. 19\u201325 (2015)","DOI":"10.1109\/SEsCPS.2015.12"}],"container-title":["Lecture Notes in Computer Science","Formal Aspects of Component Software"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-28934-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T17:15:28Z","timestamp":1692206128000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-28934-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319289335","9783319289342"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-28934-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}