{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:45:48Z","timestamp":1742913948125,"version":"3.40.3"},"publisher-location":"Cham","reference-count":10,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030731120"},{"type":"electronic","value":"9783030731137"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-73113-7_9","type":"book-chapter","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T15:03:19Z","timestamp":1626966199000},"page":"97-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Impact of Domain Knowledge Quality on Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Reed","family":"Sogabe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh Bahadur","family":"Malla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaru","family":"Sogabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kitsuyoshi","family":"Sakamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomah","family":"Sogabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,23]]},"reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/978-3-030-30484-3_48","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Deep Learning","author":"R Ramamurthy","year":"2019","unstructured":"Ramamurthy, R., Bauckhage, C., Sifa, R., Sch\u00fccker, J., Wrobel, S.: Leveraging domain knowledge for reinforcement learning using MMC architectures. In: Tetko, I.V., K\u016frkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11728, pp. 595\u2013607. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30484-3_48"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Oh, M., Iyengar, G.: Sequential Anomaly Detection using Inverse Reinforcement Learning. arXiv:2004.10398 (2020)","DOI":"10.1145\/3292500.3330932"},{"key":"9_CR3","unstructured":"Wulfmeier, M., Ondruska, P., Posner, I.: Maximum entropy deep inverse reinforcement learning, arXiv:1507.04888 (2015)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. IEEE Int. Conf. Robot. Autom. (ICRA), 6292\u20136299(2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"9_CR5","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms. arXiv:1707.06347 (2017)"},{"key":"9_CR6","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, MA (1998)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Russell, S.: Learning agents for uncertain environments. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, ACM, 101\u2013 103 (1998)","DOI":"10.1145\/279943.279964"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Abbeel, P., Andrew, N.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings, Twenty-First International Conference on Machine Learning (2004). https:\/\/doi.org\/10.1007\/978-0-387-30164-8_417","DOI":"10.1007\/978-0-387-30164-8_417"},{"key":"9_CR9","unstructured":"Price, B., Boutilier, C.: A Bayesian Approach to Imitation in Reinforcement Learning, In: IJCAI 2003: Proceedings of the 18th International Joint Conference on Artificial Intelligence, pp. 712\u2013717 (2003)"},{"key":"9_CR10","unstructured":"Ziebart, B.D., Maas, A., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, 1433\u20131438 (2008)"}],"container-title":["Advances in Intelligent Systems and Computing","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-73113-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T15:04:12Z","timestamp":1626966252000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-73113-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030731120","9783030731137"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-73113-7_9","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"JSAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Annual Conference of the Japanese Society for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kumamoto-ken","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"jsai2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ai-gakkai.or.jp\/jsai2020\/en","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}