{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:13:27Z","timestamp":1742940807873,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863791"},{"type":"electronic","value":"9783030863807"}],"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\/978-3-030-86380-7_39","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:03:14Z","timestamp":1631275394000},"page":"481-492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Plan via a Multi-step Policy Regression Method"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2423-9852","authenticated-orcid":false,"given":"Stefan","family":"Wagner","sequence":"first","affiliation":[]},{"given":"Michael","family":"Janschek","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Uelwer","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Harmeling","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"39_CR1","doi-asserted-by":"publisher","unstructured":"Barto, A., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete Event Dyn. Syst. Theory Appl. 13 (2002). https:\/\/doi.org\/10.1023\/A:1025696116075","DOI":"10.1023\/A:1025696116075"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. arXiv e-prints arXiv:1207.4708, July 2012","DOI":"10.1613\/jair.3912"},{"key":"39_CR3","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for openai gym. https:\/\/github.com\/maximecb\/gym-minigrid (2018)"},{"key":"39_CR4","unstructured":"Czarnecki, W.M., Pascanu, R., Osindero, S., Jayakumar, S.M., Swirszcz, G., Jaderberg, M.: Distilling Policy Distillation. arXiv e-prints arXiv:1902.02186, February 2019"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"De Asis, K., Hernandez-Garcia, J.F., Zacharias Holland, G., Sutton, R.S.: Multi-step reinforcement learning: a unifying algorithm. arXiv e-prints arXiv:1703.01327, March 2017","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"39_CR6","unstructured":"Efroni, Y., Dalal, G., Scherrer, B., Mannor, S.: Beyond the one step greedy approach in reinforcement learning. arXiv e-prints arXiv:1802.03654, February 2018"},{"key":"39_CR7","unstructured":"Guez, A., et al.: An investigation of model-free planning (2019)"},{"issue":"2","key":"39_CR8","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TSSC.1968.300136","volume":"4","author":"PE Hart","year":"1968","unstructured":"Hart, P.E., Nilsson, N.J., Raphael, B.: A formal basis for the heuristic determination of minimum cost paths. IEEE Trans. Syst. Sci. Cybern. 4(2), 100\u2013107 (1968)","journal-title":"IEEE Trans. Syst. Sci. Cybern."},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Lakshminarayanan, A.S., Sharma, S., Ravindran, B.: Dynamic action repetition for deep reinforcement learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 2133\u20132139. AAAI 2017. AAAI Press (2017)","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"39_CR10","unstructured":"Lee, J., Lee, B.J., Kim, K.E.: Reinforcement learning for control with multiple frequencies. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 3254\u20133264. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/216f44e2d28d4e175a194492bde9148f-Paper.pdf"},{"key":"39_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"39_CR12","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Ning, L., Shen, X.: Deep reuse: streamline CNN inference on the fly via coarse-grained computation reuse. In: Proceedings of the ACM International Conference on Supercomputing, pp. 438\u2013448 (2019)","DOI":"10.1145\/3330345.3330384"},{"key":"39_CR14","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.procs.2018.01.054","volume":"123","author":"AI Panov","year":"2018","unstructured":"Panov, A.I., Yakovlev, K.S., Suvorov, R.: Grid path planning with deep reinforcement learning: preliminary results. Procedia Comput. Sci. 123, 347\u2013353 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"39_CR15","unstructured":"Rusu, A.A., et al.: Policy Distillation. arXiv e-prints arXiv:1511.06295, November 2015"},{"key":"39_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/3-540-46084-5_132","volume-title":"Artificial Neural Networks \u2014 ICANN 2002","author":"R Schoknecht","year":"2002","unstructured":"Schoknecht, R., Riedmiller, M.: Speeding-up reinforcement learning with multi-step actions. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 813\u2013818. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-46084-5_132"},{"key":"39_CR17","unstructured":"Sutton, R., Precup, D., Singh, S.: Intra-option learning about temporally abstract actions, pp. 556\u2013564 (1998)"},{"issue":"1\u20132","key":"39_CR18","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":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86380-7_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T23:43:42Z","timestamp":1673221422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86380-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863791","9783030863807"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86380-7_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","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":"265","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":"4","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":"53% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}