{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T21:12:11Z","timestamp":1762809131452,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030839055"},{"type":"electronic","value":"9783030839062"}],"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\/978-3-030-83906-2_20","type":"book-chapter","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T23:05:04Z","timestamp":1629846304000},"page":"251-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Human-in-the-Loop Learning Methods Toward Safe DL-Based Autonomous Systems: A Review"],"prefix":"10.1007","author":[{"given":"Prajit T.","family":"Rajendran","sequence":"first","affiliation":[]},{"given":"Huascar","family":"Espinoza","sequence":"additional","affiliation":[]},{"given":"Agnes","family":"Delaborde","sequence":"additional","affiliation":[]},{"given":"Chokri","family":"Mraidha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,25]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","first-page":"106685","DOI":"10.1016\/j.knosys.2020.106685","volume":"214","author":"A Heuilleta","year":"2020","unstructured":"Heuilleta, A., Couthouis, F., et al.: Explainability in deep reinforcement learning. Knowl.-Based Syst. 214, 106685 (2020)","journal-title":"Knowl.-Based Syst."},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., et al.: The limitations of deep learning in adversarial settings. In: 1st IEEE European Symposium on Security and Privacy, Saarbrucken, Germany. IEEE (2016)","DOI":"10.1109\/EuroSP.2016.36"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, R., Kamar, E., Nushi, B., Dey, D., Shah, J., Horvitz, E.: Overcoming blind spots in the real world: leveraging complementary abilities for joint execution. In: AAAI, pp. 6137\u20136145 (2019)","DOI":"10.1609\/aaai.v33i01.33016137"},{"key":"20_CR4","unstructured":"SAE International, Taxonomy and definitions for terms related to driving automation systems for on-road motor vehicles, SAE International (J3016) (2018)"},{"key":"20_CR5","unstructured":"International Organization for Standardization: ISO 26262-1:2018 Road vehicles - Functional safety. Standard, International Organization for Standardization, Geneva, CH (2018)"},{"key":"20_CR6","unstructured":"International Organization for Standardization: ISO\/PAS 21448:2019 Road vehicles - Safety of the intended functionality. Standard, International Organization for Standardization, Geneva, CH (2019)"},{"key":"20_CR7","unstructured":"Systems and software engineering \u2014 Vocabulary, ISO\/IEC\/IEEE 24765:2017 (2017)"},{"key":"20_CR8","unstructured":"Arnez, F., Espinoza, H., et al.: A comparison of uncertainty estimation approaches in deep learning components for autonomous vehicle applications. In: Workshop AISafety 2020 - Workshop in Artificial Intelligence Safety (2020)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Kamar, E., et al.: Identifying unknown unknowns in the open world: representations and policies for guided exploration. In: NIPS Workshop on Reliability in ML (2016)","DOI":"10.1609\/aaai.v31i1.10821"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"McAllister, R., Kahn, G., et al.: Robustness to out-of-distribution inputs via task-aware generative uncertainty. In: International Conference on Robotics and Automation (ICRA), Palais des congres de Montreal, Montreal, Canada, 20\u201324 May 2019 (2019)","DOI":"10.1109\/ICRA.2019.8793552"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Geiger, A., Liu, D., et al.: TadGAN: time series anomaly detection using generative adversarial networks. In: IEEE International Conference on Big Data (Big Data) Atlanta, Georgia, USA, 10\u201313 December 2020 (2020)","DOI":"10.1109\/BigData50022.2020.9378139"},{"key":"20_CR12","unstructured":"Amodei, D., Olah, C., et al.: Concrete Problems in AI Safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"20_CR13","unstructured":"Waytowich, N.R., Goecks, V.G., et al.: Cycle-of-Learning for Autonomous Systems from Human Interaction. arXiv preprint arXiv:1808.09572 (2018)"},{"key":"20_CR14","unstructured":"Goecks, V.G.: Human-in-the-loop methods for data-driven and reinforcement learning systems. Ph.D. thesis (2020)"},{"key":"20_CR15","unstructured":"Settles, B.: Active learning literature survey, Computer Sciences Technical report 1648 University of Wisconsin-Madison (2010)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Druck, G., Settles, B., McCallum, A.: Active learning by labeling features. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 81\u201390. ACL Press (2009)","DOI":"10.3115\/1699510.1699522"},{"key":"20_CR17","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1023\/A:1007330508534","volume":"28","author":"Y Freund","year":"1997","unstructured":"Freund, Y., Seung, H.S., Shamir, E., Tishby, N.: Selective samping using the query by committee algorithm. Mach. Learn. 28, 133\u2013168 (1997)","journal-title":"Mach. Learn."},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., et al.: Behavioral cloning from observation. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), Stockholm, Sweden, July 2018","DOI":"10.24963\/ijcai.2018\/687"},{"key":"20_CR19","unstructured":"Goecks, V.G., Gremillion, G.M., et al.: Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments. In: International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2020), Auckland, New Zealand, 9\u201313 May 2020 (2020)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Farag, W., Saleh, Z., et al.: Behavior cloning for autonomous driving using convolutional neural networks. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018), Stockholm, Sweden, July 2018","DOI":"10.1109\/3ICT.2018.8855753"},{"key":"20_CR21","unstructured":"Duan, Y., Andrychowicz, M., et al.: One-shot imitation learning. In: Advances in Neural Information Processing Systems 30 (NIPS 2017) (2017)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Muller, M., et al.: End-to-end driving via conditional imitation learning. In: IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Queensland, Australia, 21\u201325 May 2018 (2018)","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"20_CR24","unstructured":"Ho, J., Ermon, S.: Generative Adversarial Imitation Learning. arXiv preprint arXiv:1606.03476 (2016)"},{"key":"20_CR25","unstructured":"Schulman, J., Levine, S., et al.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 1889\u20131897, July 2015"},{"key":"20_CR26","unstructured":"Lacotte, J., Ghavamzadeh, M., et al.: Risk-sensitive generative adversarial imitation learning. In: The 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Canary Islands, 9\u201311 April 2018 (2018)"},{"key":"20_CR27","unstructured":"Torabi, F., Warnell, G., et al.: Generative Adversarial Imitation from Observation. arXiv preprint arXiv:1807.06158 (2018)"},{"key":"20_CR28","unstructured":"Zo\u0142na, K., Reed, S., et al.: Task-relevant adversarial imitation learning. In: Conference on Robot Learning (CoRL), 16\u201318 November 2020 (2020)"},{"key":"20_CR29","unstructured":"Knox, W.B., Stone, P.: TAMER: training an agent manually via evaluative reinforcement. In: The 7th IEEE International Conference on Development and Learning, pp. 292\u2013297 (2008)"},{"key":"20_CR30","unstructured":"Knox, W.B., Stone, P., et al.: Learning from feedback on actions past and intended. In: The 7th ACM\/IEEE International Conference on Human-Robot Interaction (HRI), Boston, Massachusetts, USA, 5\u20138 March 2012 (2012)"},{"key":"20_CR31","unstructured":"Vien, N.A., Ertel, W.: Reinforcement learning combined with human feedback in continuous state and action spaces. In: IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL) SSan Diego, California, USA, 7\u20139 November 2012 (2012)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Warnell, G., Waytowich, N., et al.: Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces. arXiv preprint arXiv:1709.10163 (2017)","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"20_CR33","unstructured":"Arakawa, R., Kobayashi, S., et al.: DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback. arXiv preprint arXiv:1810.11748 (2018)"},{"key":"20_CR34","unstructured":"Christiano, P.F., Leike, J., et al.: Deep reinforcement learning from human preferences. arXiv preprint arXiv:1706.03741 (2017)"},{"key":"20_CR35","unstructured":"Saunders, W., Sastry, G., et al.: Trial without Error: Towards Safe Reinforcement Learning via Human Intervention. arXiv preprint arXiv:1707.05173v1 (2017)"},{"key":"20_CR36","unstructured":"Prakash, B., Khatwani, M., et al.: Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention. arXiv preprint arXiv:1903.09328 (2019)"},{"issue":"1","key":"20_CR37","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.patrec.2017.06.017","volume":"105","author":"A Jevtic","year":"2018","unstructured":"Jevtic, A., Colom\u00e9, A., et al.: Robot motion adaptation through user intervention and reinforcement learning. Pattern Recogn. Lett. 105(1), 67\u201375 (2018)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR38","unstructured":"Ross, S., Gordon, G.J.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS) 2011, Fort Lauderdale, FL, USA. Volume 15 of JMLR: W&CP 15 (2011)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cho, K.: Query-efficient imitation learning for end-to-end simulated driving. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI 2017) (2017)","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Menda, K., Driggs-Campbell, K., et al.: EnsembleDAgger: a Bayesian approach to safe imitation learning. In: Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2019) (2019)","DOI":"10.1109\/IROS40897.2019.8968287"}],"container-title":["Lecture Notes in Computer Science","Computer Safety, Reliability, and Security. SAFECOMP 2021 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-83906-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T17:42:20Z","timestamp":1710265340000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-83906-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030839055","9783030839062"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-83906-2_20","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":"25 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SAFECOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Safety, Reliability, and Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"York","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"7 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"safecomp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/safecomp2021.hosted.york.ac.uk\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"76","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":"17","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":"0","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":"22% - 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":"4.2","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":"From the workshops 26 full and 4 short papers were accepted for publication.","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)"}}]}}