{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:36:22Z","timestamp":1742913382491,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"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_53","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:03:14Z","timestamp":1631275394000},"page":"650-661","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Advances in Adaptive Skill Acquisition"],"prefix":"10.1007","author":[{"given":"Juraj","family":"Holas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Farka\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"53_CR2","unstructured":"Bakker, B., Schmidhuber, J.: Hierarchical reinforcement learning with subpolicies specializing for learned subgoals. In: International Conference on Neural Networks and Computational Intelligence, pp. 125\u2013130 (2004)"},{"key":"53_CR3","unstructured":"Garage contributors: Garage: A toolkit for reproducible reinforcement learning research. https:\/\/github.com\/rlworkgroup\/garage (2019)"},{"issue":"1","key":"53_CR4","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the maxq value function decomposition. J. Artif. Intell. Res. 13(1), 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"53_CR5","unstructured":"Dillinger, V.: Abstract state space construction in hierarchical reinforcement learning. Ph.D. thesis, Comenius University in Bratislava (2019)"},{"key":"53_CR6","unstructured":"Florensa, C., Duan, Y., Abbeel, P.: Stochastic neural networks for hierarchical reinforcement learning. In: International Conference on Learning Representations (2017)"},{"key":"53_CR7","unstructured":"Goel, S., Huber, M.: Subgoal discovery for hierarchical reinforcement learning using learned policies. In: Florida AI Research Society Conference, pp. 346\u2013350 (2003)"},{"key":"53_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/978-3-030-61616-8_31","volume-title":"Artificial Neural Networks and Machine Learning","author":"J Holas","year":"2020","unstructured":"Holas, J., Farka\u0161, I.: Adaptive skill acquisition in hierarchical reinforcement learning. In: Farka\u0161, I., Masulli, P., Wermter, S. (eds.) ICANN 2020. LNCS, vol. 12397, pp. 383\u2013394. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61616-8_31"},{"key":"53_CR9","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"53_CR10","unstructured":"Konidaris, G., Barto, A.G.: Skill discovery in continuous reinforcement learning domains using skill chaining. In: Advances in Neural Information Processing Systems, pp. 1015\u20131023 (2009)"},{"key":"53_CR11","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In: Advances in Neural Information Processing Systems, pp. 3675\u20133683 (2016)"},{"key":"53_CR12","unstructured":"Levy, A., Konidaris, G., Platt, R., Saenko, K.: Learning multi-level hierarchies with hindsight. In: International Conference on Learning Representations (2018)"},{"key":"53_CR13","unstructured":"Li, A.C., Florensa, C., Clavera, I., Abbeel, P.: Sub-policy adaptation for hierarchical reinforcement learning. In: International Conference on Learning Representations (2020)"},{"key":"53_CR14","first-page":"361","volume":"1","author":"A McGovern","year":"2001","unstructured":"McGovern, A., Barto, A.G.: Automatic discovery of subgoals in reinforcement learning using diverse density. Int. Conf. Mach. Learn. 1, 361\u2013368 (2001)","journal-title":"Int. Conf. Mach. Learn."},{"key":"53_CR15","doi-asserted-by":"crossref","unstructured":"McGovern, E.A., Barto, A.G.: Autonomous discovery of temporal abstractions from interaction with an environment. Ph.D. thesis, University of Massachusetts at Amherst (2002)","DOI":"10.1007\/3-540-45622-8_34"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Menache, I., Mannor, S., Shimkin, N.: Q-cut\u2014dynamic discovery of sub-goals in reinforcement learning. In: European Conference on Machine Learning, pp. 295\u2013306 (2002)","DOI":"10.1007\/3-540-36755-1_25"},{"key":"53_CR17","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3389\/fnbot.2013.00011","volume":"7","author":"JH Metzen","year":"2013","unstructured":"Metzen, J.H., Kirchner, F.: Incremental learning of skill collections based on intrinsic motivation. Front. Neurorobotics 7, 11 (2013)","journal-title":"Front. Neurorobotics"},{"key":"53_CR18","unstructured":"Moerman, W.: Hierarchical reinforcement learning: Assignment of behaviours to subpolicies by self-organization. Ph.D. thesis, Cognitive Artificial Intelligence, Utrecht University (2009)"},{"key":"53_CR19","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 3303\u20133313 (2018)"},{"key":"53_CR20","unstructured":"Parr, R., Russell, S.J.: Reinforcement learning with hierarchies of machines. In: Advances in Neural Information Processing Systems, pp. 1043\u20131049 (1998)"},{"issue":"2","key":"53_CR21","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1080\/09540099550039318","volume":"7","author":"A Robins","year":"1995","unstructured":"Robins, A.: Catastrophic forgetting, rehearsal and pseudorehearsal. Connection Sci. 7(2), 123\u2013146 (1995)","journal-title":"Connection Sci."},{"key":"53_CR22","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"53_CR23","unstructured":"Shu, T., Xiong, C., Socher, R.: Hierarchical and interpretable skill acquisition in multi-task reinforcement learning. In: International Conference on Learning Representations (2018)"},{"key":"53_CR24","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, 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_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T23:44:35Z","timestamp":1673221475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86380-7_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863791","9783030863807"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86380-7_53","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)"}}]}}