{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:05:59Z","timestamp":1743116759730,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030030971"},{"type":"electronic","value":"9783030030988"}],"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\/978-3-030-03098-8_27","type":"book-chapter","created":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T12:27:33Z","timestamp":1540297653000},"page":"431-439","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Abstracting Reinforcement Learning Agents with Prior Knowledge"],"prefix":"10.1007","author":[{"given":"Nicolas","family":"Bougie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryutaro","family":"Ichise","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,24]]},"reference":[{"unstructured":"Andre, D., Russell, S.J.: State abstraction for programmable reinforcement learning agents (2002)","key":"27_CR1"},{"key":"27_CR2","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"M. G. Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents (2013)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"7","key":"27_CR3","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1177\/0278364911404092","volume":"30","author":"B Boots","year":"2011","unstructured":"Boots, B., Siddiqi, S.M., Gordon, G.J.: Closing the learning-planning loop with predictive state representations. Int. J. Robot. Res. 30(7), 954\u2013966 (2011)","journal-title":"Int. J. Robot. Res."},{"doi-asserted-by":"crossref","unstructured":"Bougie, N., Ichise, R.: Deep reinforcement learning boosted by external knowledge. In: Proceedings of the 33rd Annual ACM Symposium on Applied Computing, pp. 331\u2013338. ACM (2018)","key":"27_CR4","DOI":"10.1145\/3167132.3167165"},{"unstructured":"d\u2019Avila Garcez, A., Resende Riquetti Dutra, A., Alonso, E.: Towards Symbolic Reinforcement Learning with Common Sense. ArXiv e-prints, April 2018","key":"27_CR5"},{"issue":"1\u20132","key":"27_CR6","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1007694015589","volume":"43","author":"S D\u017eeroski","year":"2001","unstructured":"D\u017eeroski, S., De Raedt, L., Driessens, K.: Relational reinforcement learning. Mach. Learn. 43(1\u20132), 7\u201352 (2001)","journal-title":"Mach. Learn."},{"doi-asserted-by":"crossref","unstructured":"Gambardella, L.M., Dorigo, M.: Ant-Q: a reinforcement learning approach to the traveling salesman problem. In: Machine Learning Proceedings 1995, pp. 252\u2013260. Elsevier (1995)","key":"27_CR7","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"unstructured":"Garnelo, M., Arulkumaran, K., Shanahan, M.: Towards deep symbolic reinforcement learning. In: Abbeel, P., Chen, P., Silver, D., Singh, S. (eds.) NIPS. Neural Information Processing Systems Foundation, La Jolla, California (2016)","key":"27_CR8"},{"unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs (2015)","key":"27_CR9"},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)","key":"27_CR10"},{"key":"27_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/978-3-319-18356-5_20","volume-title":"Advances in Artificial Intelligence","author":"M Mashayekhi","year":"2015","unstructured":"Mashayekhi, M., Gras, R.: Rule extraction from random forest: the RF+HC methods. In: Barbosa, D., Milios, E. (eds.) CANADIAN AI 2015. LNCS (LNAI), vol. 9091, pp. 223\u2013237. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18356-5_20"},{"unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)","key":"27_CR12"},{"key":"27_CR13","volume-title":"Japanese Candlestick Charting Techniques: A Contemporary Guide to the Ancient Investment Techniques of the Far East","author":"S Nison","year":"2001","unstructured":"Nison, S.: Japanese Candlestick Charting Techniques: A Contemporary Guide to the Ancient Investment Techniques of the Far East. Penguin, London (2001)"},{"unstructured":"Papudesi, V., Huber, M.: Learning behaviorally grounded state representations for reinforcement learning agents (2006)","key":"27_CR14"},{"key":"27_CR15","first-page":"463","volume":"98","author":"J Randl\u00f8v","year":"1998","unstructured":"Randl\u00f8v, J., Alstr\u00f8m, P.: Learning to drive a bicycle using reinforcement learning and shaping. Proc. ICML 98, 463\u2013471 (1998)","journal-title":"Proc. ICML"},{"doi-asserted-by":"crossref","unstructured":"Rosencrantz, M., Gordon, G., Thrun, S.: Learning low dimensional predictive representations. In: Proceedings of the Twenty-First ICML. ACM (2004)","key":"27_CR16","DOI":"10.1145\/1015330.1015441"},{"unstructured":"Singh, S.P., Jaakkola, T., Jordan, M.I.: Reinforcement learning with soft state aggregation. In: Proceedings of NIPS, pp. 361\u2013368 (1995)","key":"27_CR17"},{"issue":"1\u20133","key":"27_CR18","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00114726","volume":"22","author":"SP Singh","year":"1996","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Mach. Learn. 22(1\u20133), 123\u2013158 (1996)","journal-title":"Mach. Learn."},{"unstructured":"Sutton, R.S.: Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Proceedings of NIPS, pp. 1038\u20131044 (1996)","key":"27_CR19"},{"key":"27_CR20","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"3\u20134","key":"27_CR21","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","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."}],"container-title":["Lecture Notes in Computer Science","PRIMA 2018: Principles and Practice of Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03098-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T18:04:38Z","timestamp":1703181878000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03098-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030030971","9783030030988"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03098-8_27","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":"24 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRIMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Principles and Practice of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"prima2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2018.prima-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"103","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":"25","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":"33","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":"24% - 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","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":"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)"}}]}}