{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T21:36:43Z","timestamp":1726004203878},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030013691"},{"type":"electronic","value":"9783030013707"}],"license":[{"start":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:00:00Z","timestamp":1546214400000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-01370-7_33","type":"book-chapter","created":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:53:36Z","timestamp":1546217616000},"page":"414-427","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HI-VAL: Iterative Learning of Hierarchical Value Functions for Policy Generation"],"prefix":"10.1007","author":[{"given":"Roberto","family":"Capobianco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Riccio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,31]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Agostini, A., Celaya, E.: Reinforcement learning with a Gaussian mixture model. In: The 2010 International Joint Conference on Neural Networks, pp. 1\u20138, July 2010","DOI":"10.1109\/IJCNN.2010.5596306"},{"key":"33_CR2","unstructured":"Anand, A., Grover, A., Mausam, M., Singla, P.: ASAP-UCT: abstraction of state-action pairs in UCT. In: Proceedings of the 24th International Conference on Artificial Intelligence, IJCAI 2015, pp. 1509\u20131515. AAAI Press (2015). http:\/\/dl.acm.org\/citation.cfm?id=2832415.2832459"},{"issue":"2\u20133","key":"33_CR3","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":"33_CR4","unstructured":"Bagnell, J.A., Schneider, J.G.: Autonomous helicopter control using reinforcement learning policy search methods. In: 2001 IEEE International Conference on Robotics and Automation, vol.\u00a02, pp. 1615\u20131620 (2001)"},{"issue":"3","key":"33_CR5","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/JAS.2014.7004680","volume":"1","author":"G Chowdhary","year":"2014","unstructured":"Chowdhary, G., Liu, M., Grande, R., Walsh, T., How, J., Carin, L.: Off-policy reinforcement learning with Gaussian processes. IEEE\/CAA J. Autom. Sinica 1(3), 227\u2013238 (2014)","journal-title":"IEEE\/CAA J. Autom. Sinica"},{"key":"33_CR6","unstructured":"Clair, A.S., Saldanha, C., Boteanu, A., Chernova, S.: Interactive hierarchical task learning via crowdsourcing for robot adaptability. In: Refereed Workshop Planning for Human-Robot Interaction: Shared Autonomy and Collaborative Robotics at Robotics: Science and Systems, Ann Arbor, Michigan. RSS (2016)"},{"key":"33_CR7","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artif. Intell. Res. (JAIR) 13, 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res. (JAIR)"},{"key":"33_CR8","unstructured":"Erol, K., Hendler, J., Nau, D.S.: HTN planning: complexity and expressivity. In: the Twelfth National Conference on Artificial Intelligence, vol. 2, AAAI 1994, pp. 1123\u20131128. American Association for Artificial Intelligence, Menlo Park (1994). http:\/\/dl.acm.org\/citation.cfm?id=199480.199459"},{"key":"33_CR9","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1613\/jair.5483","volume":"60","author":"J Hostetler","year":"2017","unstructured":"Hostetler, J., Fern, A., Dietterich, T.G.: Sample-based tree search with fixed and adaptive state abstractions. J. Artif. Intell. Res. 60, 717\u2013777 (2017). https:\/\/doi.org\/10.1613\/jair.5483","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"33_CR10","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0921-8890(01)00113-0","volume":"36","author":"M Jun","year":"2001","unstructured":"Jun, M., Kenji, D.: Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Rob. Autonom. Syst. 36(1), 37\u201351 (2001)","journal-title":"Rob. Autonom. Syst."},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Rob. Res. (2013)","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Kober, J., Peters, J.R.: Policy search for motor primitives in robotics. In: Advances in Neural Information Processing Systems, pp. 849\u2013856 (2009)","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"33_CR13","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Lecture Notes in Computer Science","author":"Levente Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based monte-carlo planning, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Kohl, N., Stone, P.: Policy gradient reinforcement learning for fast quadrupedal locomotion. In: 2004 IEEE International Conference on Robotics and Automation, vol.\u00a03, pp. 2619\u20132624, April 2004","DOI":"10.1109\/ROBOT.2004.1307456"},{"issue":"3","key":"33_CR15","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1177\/0278364911428653","volume":"31","author":"G Konidaris","year":"2012","unstructured":"Konidaris, G., Kuindersma, S., Grupen, R., Barto, A.: Robot learning from demonstration by constructing skill trees. Int. J. Rob. Res. 31(3), 360\u2013375 (2012)","journal-title":"Int. J. Rob. Res."},{"key":"33_CR16","unstructured":"Riccio, F., Capobianco, R., Nardi, D.: DOP: deep optimistic planning with approximate value function evaluation. In: Proceedings of the 2018 International Conference on Autonomous Agents and Multiagent Systems (AAMAS) (2018)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Riccio, F., Capobianco, R., Nardi, D.: Q-CP: learning action values for cooperative planning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8460180"},{"key":"33_CR18","unstructured":"Ross, S., Gordon, G.J., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635 (2011)"},{"key":"33_CR19","unstructured":"Schaul, T., Ring, M.: Better generalization with forecasts. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI 2013, pp. 1656\u20131662. AAAI Press (2013)"},{"key":"33_CR20","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"issue":"2","key":"33_CR21","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10994-012-5280-0","volume":"87","author":"D Silver","year":"2012","unstructured":"Silver, D., Sutton, R.S., M\u00fcller, M.: Temporal-difference search in computer Go. Mach. Learn. 87(2), 183\u2013219 (2012)","journal-title":"Mach. Learn."},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Stulp, F., Schaal, S.: Hierarchical reinforcement learning with movement primitives. In: 2011 IEEE-RAS International Conference on Humanoid Robots, pp. 231\u2013238, October 2011","DOI":"10.1109\/Humanoids.2011.6100841"},{"issue":"1\u20132","key":"33_CR23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."}],"container-title":["Advances in Intelligent Systems and Computing","Intelligent Autonomous Systems 15"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01370-7_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T08:36:14Z","timestamp":1573634174000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-01370-7_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,31]]},"ISBN":["9783030013691","9783030013707"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01370-7_33","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2018,12,31]]},"assertion":[{"value":"IAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Autonomous Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Baden-Baden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ias2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/conference.vde.com\/ias\/Pages\/Homepage.aspx","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}