{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:44:18Z","timestamp":1751013858899,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319896557"},{"type":"electronic","value":"9783319896564"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-89656-4_6","type":"book-chapter","created":{"date-parts":[[2018,4,5]],"date-time":"2018-04-05T04:53:44Z","timestamp":1522904024000},"page":"72-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Advice-Based Exploration in Model-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7734-099X","authenticated-orcid":false,"given":"Rodrigo","family":"Toro Icarte","sequence":"first","affiliation":[]},{"given":"Toryn Q.","family":"Klassen","sequence":"additional","affiliation":[]},{"given":"Richard Anthony","family":"Valenzano","sequence":"additional","affiliation":[]},{"given":"Sheila A.","family":"McIlraith","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,4,6]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Pnueli, A.: The temporal logic of programs. In: FOCS, pp. 46\u201357 (1977)","key":"6_CR1","DOI":"10.1109\/SFCS.1977.32"},{"key":"6_CR2","first-page":"213","volume":"3","author":"R Brafman","year":"2002","unstructured":"Brafman, R., Tennenholtz, M.: R-MAX - a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213\u2013231 (2002)","journal-title":"J. Mach. Learn. Res."},{"issue":"1\u20132","key":"6_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/S0004-3702(99)00071-5","volume":"116","author":"F Bacchus","year":"2000","unstructured":"Bacchus, F., Kabanza, F.: Using temporal logics to express search control knowledge for planning. Artif. Intell. 116(1\u20132), 123\u2013191 (2000)","journal-title":"Artif. Intell."},{"doi-asserted-by":"crossref","unstructured":"De Giacomo, G., Masellis, R.D., Montali, M.: Reasoning on LTL on finite traces: insensitivity to infiniteness. In: AAAI, pp. 1027\u20131033 (2014)","key":"6_CR4","DOI":"10.1609\/aaai.v28i1.8872"},{"unstructured":"Baier, J., McIlraith, S.: Planning with first-order temporally extended goals using heuristic search. In: AAAI, pp. 788\u2013795 (2006)","key":"6_CR5"},{"unstructured":"Peng, B., MacGlashan, J., Loftin, R., Littman, M., Roberts, D., Taylor, M.: A need for speed: adapting agent action speed to improve task learning from non-expert humans. In: AAMAS, pp. 957\u2013965 (2016)","key":"6_CR6"},{"issue":"1\u20132","key":"6_CR7","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S0004-3702(01)00106-0","volume":"129","author":"E Hansen","year":"2001","unstructured":"Hansen, E., Zilberstein, S.: LAO*: a heuristic search algorithm that finds solutions with loops. Artif. Intell. 129(1\u20132), 35\u201362 (2001)","journal-title":"Artif. Intell."},{"unstructured":"McCarthy, J.: Programs with common sense. RLE and MIT Computation Center (1960)","key":"6_CR8"},{"doi-asserted-by":"crossref","unstructured":"Lacerda, B., Parker, D., Hawes, N.: Optimal and dynamic planning for markov decision processes with co-safe LTL specifications. In: IROS, pp. 1511\u20131516 (2014)","key":"6_CR9","DOI":"10.1109\/IROS.2014.6942756"},{"unstructured":"Wen, M., Topcu, U.: Probably approximately correct learning in stochastic games with temporal logic specifications. In: IJCAI, pp. 3630\u20133636 (2016)","key":"6_CR10"},{"unstructured":"Andre, D., Russell, S.J.: Programmable reinforcement learning agents. In: NIPS, pp. 1019\u20131025 (2000)","key":"6_CR11"},{"doi-asserted-by":"crossref","unstructured":"Shapiro, D., Langley, P., Shachter, R.: Using background knowledge to speed reinforcement learning in physical agents. In: AA, pp. 254\u2013261 (2001)","key":"6_CR12","DOI":"10.1145\/375735.376305"},{"doi-asserted-by":"crossref","unstructured":"Isbell, C., Shelton, C.R., Kearns, M., Singh, S., Stone, P.: A social reinforcement learning agent. In: AA, pp. 377\u2013384 (2001)","key":"6_CR13","DOI":"10.1145\/375735.376334"},{"unstructured":"Knox, W.B., Stone, P.: Tamer: training an agent manually via evaluative reinforcement. In: ICDL, pp. 292\u2013297 (2008)","key":"6_CR14"},{"doi-asserted-by":"crossref","unstructured":"Judah, K., Roy, S., Fern, A., Dietterich, T.G.: Reinforcement learning via practice and critique advice. In: AAAI, pp. 481\u2013486 (2010)","key":"6_CR15","DOI":"10.1609\/aaai.v24i1.7690"},{"unstructured":"Griffith, S., Subramanian, K., Scholz, J., Isbell, C., Thomaz, A.L.: Policy shaping: integrating human feedback with reinforcement learning. In: NIPS (2013)","key":"6_CR16"},{"issue":"1\u20133","key":"6_CR17","first-page":"251","volume":"22","author":"R Maclin","year":"1996","unstructured":"Maclin, R., Shavlik, J.: Creating advice-taking reinforcement learners. Mach. Learn. 22(1\u20133), 251\u2013281 (1996)","journal-title":"Mach. Learn."},{"unstructured":"Maclin, R., Shavlik, J., Torrey, L., Walker, T., Wild, E.: Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In: AAAI, pp. 819\u2013824 (2005)","key":"6_CR18"},{"doi-asserted-by":"crossref","unstructured":"Kunapuli, G., Odom, P., Shavlik, J.W., Natarajan, S.: Guiding autonomous agents to better behaviors through human advice. In: ICDM, pp. 409\u2013418 (2013)","key":"6_CR19","DOI":"10.1109\/ICDM.2013.79"},{"issue":"1","key":"6_CR20","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TCDS.2016.2628365","volume":"9","author":"S Krening","year":"2016","unstructured":"Krening, S., Harrison, B., Feigh, K., Isbell, C., Riedl, M., Thomaz, A.: Learning from explanations using sentiment and advice in RL. IEEE Trans. Cogn. Dev. Syst. 9(1), 44\u201355 (2016)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"unstructured":"Andreas, J., Klein, D., Levine, S.: Modular multitask reinforcement learning with policy sketches. In: ICML, pp. 166\u2013175 (2017)","key":"6_CR21"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-89656-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:34:34Z","timestamp":1710354874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-89656-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319896557","9783319896564"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-89656-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 April 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Canadian AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canadian Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"8 May 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"canadianai2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.caiac.ca\/en\/conferences\/canadianai-2018\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}