{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:25:22Z","timestamp":1762953922741,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442124"},{"type":"electronic","value":"9783031442131"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44213-1_23","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"271-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Addressing Delays in\u00a0Reinforcement Learning via\u00a0Delayed Adversarial Imitation Learning"],"prefix":"10.1007","author":[{"given":"Minzhi","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yalou","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongzhe","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"issue":"3","key":"23_CR1","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TRA.2004.825271","volume":"20","author":"T Imaida","year":"2004","unstructured":"Imaida, T., Yokokohji, Y., Doi, T., Oda, M., Yoshikawa, T.: Ground-space bilateral teleoperation of ETS-VII robot arm by direct bilateral coupling under 7-s time delay condition. IEEE Trans. Robot. Autom. 20(3), 499\u2013511 (2004)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Lampe, T., Fiederer, L.D.J., Voelker, M., Knorr, A., Riedmiller, M., Ball, T.: A brain-computer interface for high-level remote control of an autonomous, reinforcement-learning-based robotic system for reaching and grasping. In: Proceedings of the 19th international conference on Intelligent User Interfaces, pp. 83\u201388 (2014)","DOI":"10.1145\/2557500.2557533"},{"issue":"1","key":"23_CR3","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1145\/149439.133106","volume":"20","author":"E Altman","year":"1992","unstructured":"Altman, E., Nain, P.: Closed-loop control with delayed information. ACM Sigmetrics Perform. Eval. Rev. 20(1), 193\u2013204 (1992)","journal-title":"ACM Sigmetrics Perform. Eval. Rev."},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.neucom.2021.04.015","volume":"450","author":"B Chen","year":"2021","unstructured":"Chen, B., Mengdi, X., Li, L., Zhao, D.: Delay-aware model-based reinforcement learning for continuous control. Neurocomputing 450, 119\u2013128 (2021)","journal-title":"Neurocomputing"},{"key":"23_CR5","unstructured":"Firoiu, V., Ju, T., Tenenbaum, J.: At human speed: deep reinforcement learning with action delay. arXiv preprint arXiv:1810.07286 (2018)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Schuitema, E., Bu\u015foniu, L., Babu\u0161ka, R., Jonker, P.: Control delay in reinforcement learning for real-time dynamic systems: a memoryless approach. In: 2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3226\u20133231. IEEE (2010)","DOI":"10.1109\/IROS.2010.5650345"},{"key":"23_CR7","unstructured":"Ramstedt, S., Bouteiller, Y., Beltrame, G., Pal, C., Binas, J.: Reinforcement learning with random delays. arXiv preprint arXiv:2010.02966 (2020)"},{"key":"23_CR8","unstructured":"Maran, D.: Delayed reinforcement learning, an imitation game (2021)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Bain, M., Sammut, C.: A framework for behavioural cloning. In: Machine Intelligence 15, pp. 103\u2013129 (2000)","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"23_CR10","unstructured":"Pomerleau, D.A.: ALVINN: an autonomous land vehicle in a neural network. In: Advances in Neural Information Processing Systems, vol. 1 (1988)"},{"key":"23_CR11","unstructured":"Finn, C., Christiano, P., Abbeel, P., Levine, S.: A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models. arXiv preprint arXiv:1611.03852 (2016)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 1 (2004)","DOI":"10.1145\/1015330.1015430"},{"issue":"11","key":"23_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"23_CR14","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"23_CR15","unstructured":"Fu, J., Luo, K., Levine, S.: Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248 (2017)"},{"key":"23_CR16","unstructured":"Ramstedt, S., Pal, C.: Real-time reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"4","key":"23_CR17","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/TAC.2003.809799","volume":"48","author":"KV Katsikopoulos","year":"2003","unstructured":"Katsikopoulos, K.V., Engelbrecht, S.E.: Markov decision processes with delays and asynchronous cost collection. IEEE Trans. Autom. Control 48(4), 568\u2013574 (2003)","journal-title":"IEEE Trans. Autom. Control"},{"key":"23_CR18","unstructured":"Kostrikov, I., Agrawal, K.K., Dwibedi, D., Levine, S., Tompson, J.: Discriminator-actor-critic: addressing sample inefficiency and reward bias in adversarial imitation learning. arXiv preprint arXiv:1809.02925 (2018)"},{"key":"23_CR19","unstructured":"Haarnoja, T., Zhou, A., Abbeel, A., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"23_CR20","unstructured":"Devroye, L., Mehrabian, A., Reddad, T.: The total variation distance between high-dimensional gaussians. arXiv preprint arXiv:1810.08693 (2018)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"23_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44213-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T06:44:35Z","timestamp":1703227475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44213-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442124","9783031442131"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44213-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","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":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","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":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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)"}},{"value":"type of other papers accepted : 9 Abstract","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)"}}]}}