{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:06:18Z","timestamp":1726059978500},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030352875"},{"type":"electronic","value":"9783030352882"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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\/978-3-030-35288-2_17","type":"book-chapter","created":{"date-parts":[[2019,11,24]],"date-time":"2019-11-24T19:02:57Z","timestamp":1574622177000},"page":"203-214","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Solving Safety Problems with Ensemble Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Leonardo A.","family":"Ferreira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thiago F.","family":"dos Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinaldo A. C.","family":"Bianchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo E.","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,25]]},"reference":[{"issue":"2","key":"17_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1145\/3243064.3243067","volume":"18","author":"N Bougie","year":"2018","unstructured":"Bougie, N., Cheng, L.K., Ichise, R.: Combining deep reinforcement learning with prior knowledge and reasoning. SIGAPP Appl. Comput. Rev. 18(2), 33\u201345 (2018)","journal-title":"SIGAPP Appl. Comput. Rev."},{"key":"17_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-45014-9_1","volume-title":"Multiple Classifier Systems","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Ensemble methods in machine learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1\u201315. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45014-9_1"},{"key":"17_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-92058-0_1","volume-title":"Recent Trends and Future Technology in Applied Intelligence","author":"LA Ferreira","year":"2018","unstructured":"Ferreira, L.A., Bianchi, R.A.C., Santos, P.E., de Mantaras, R.L.: A method for the online construction of the set of states of a Markov decision process using answer set programming. In: Mouhoub, M., Sadaoui, S., Ait Mohamed, O., Ali, M. (eds.) IEA\/AIE 2018. LNCS (LNAI), vol. 10868, pp. 3\u201315. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-92058-0_1"},{"key":"17_CR4","unstructured":"d\u2019Avila Garcez, A.S., Dutra, A.R.R., Alonso, E.: Towards symbolic reinforcement learning with common sense. CoRR abs\/1804.08597 (2018)"},{"key":"17_CR5","unstructured":"Garnelo, M., Arulkumaran, K., Shanahan, M.: Towards deep symbolic reinforcement learning. In: Deep Reinforcement Learning Workshop at the 30th Conference on Neural Information Processing Systems (2016)"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.cobeha.2018.12.010","volume":"29","author":"M Garnelo","year":"2019","unstructured":"Garnelo, M., Shanahan, M.: Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Curr. Opin. Behav. Sci. 29, 17\u201323 (2019)","journal-title":"Curr. Opin. Behav. Sci."},{"key":"17_CR7","unstructured":"Leike, J., et al.: AI safety gridworlds. CoRR abs\/1711.09883 (2017)"},{"key":"17_CR8","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.artint.2016.07.004","volume":"241","author":"M Leonetti","year":"2016","unstructured":"Leonetti, M., Iocchi, L., Stone, P.: A synthesis of automated planning and reinforcement learning for efficient, robust decision-making. Artif. Intell. 241, 103\u2013130 (2016)","journal-title":"Artif. Intell."},{"key":"17_CR9","unstructured":"Liang, Y., Machado, M.C., Talvitie, E., Bowling, M.: State of the art control of Atari games using shallow reinforcement learning. In: Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016, pp. 485\u2013493. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2016)"},{"key":"17_CR10","unstructured":"Lu, K., Zhang, S., Stone, P., Chen, X.: Robot representing and reasoning with knowledge from reinforcement learning. CoRR abs\/1809.11074 (2018)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Lyu, D., Yang, F., Liu, B., Gustafson, S.: SDRL: interpretable and data-efficient deep reinforcement learning leveraging symbolic planning. CoRR abs\/1811.00090 (2018)","DOI":"10.1609\/aaai.v33i01.33012970"},{"key":"17_CR12","unstructured":"McCarthy, J.: Elaboration tolerance (1999)"},{"issue":"7540","key":"17_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"17_CR14","volume-title":"Ontology: A Practical Guide","author":"A Pease","year":"2011","unstructured":"Pease, A.: Ontology: A Practical Guide. Articulate Software Press, Angwin (2011)"},{"issue":"7587","key":"17_CR15","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","journal-title":"Nature"},{"issue":"7676","key":"17_CR16","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"key":"17_CR17","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018)","edition":"2"},{"issue":"3","key":"17_CR18","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"issue":"3\u20134","key":"17_CR19","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."},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Yang, F., Lyu, D., Liu, B., Gustafson, S.: PEORL: integrating symbolic planning and hierarchical reinforcement learning for robust decision-making. CoRR abs\/1804.07779 (2018)","DOI":"10.24963\/ijcai.2018\/675"},{"key":"17_CR21","unstructured":"Zamani, M.A., Magg, S., Weber, C., Wermter, S.: Deep reinforcement learning using symbolic representation for performing spoken language instructions. In: 2nd Workshop on Behavior Adaptation, Interaction and Learning for Assistive Robotics on Robot and Human Interactive Communication (2017)"}],"container-title":["Lecture Notes in Computer Science","AI 2019: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-35288-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T17:02:49Z","timestamp":1665075769000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-35288-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030352875","9783030352882"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-35288-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Adelaide, SA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nugget.unisa.edu.au\/AI2019\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"115","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"48","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}