{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:15:33Z","timestamp":1743120933510,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030922696"},{"type":"electronic","value":"9783030922702"}],"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\/978-3-030-92270-2_35","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T11:06:00Z","timestamp":1638788760000},"page":"405-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generative Adversarial Negative Imitation Learning from\u00a0Noisy Demonstrations"],"prefix":"10.1007","author":[{"given":"Xin","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,7]]},"reference":[{"key":"35_CR1","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":"4","key":"35_CR2","first-page":"343","volume":"2","author":"D Angluin","year":"1988","unstructured":"Angluin, D., Laird, P.: Learning from noisy examples. Mach. Learn. 2(4), 343\u2013370 (1988)","journal-title":"Mach. Learn."},{"key":"35_CR3","unstructured":"Brown, D.S., Goo, W., Nagarajan, P., Niekum, S.: Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations. arXiv e-prints pp. arXiv-1904 (2019)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Chen, Z., Wang, D.: Adaptive adversarial training for meta reinforcement learning. arXiv preprint arXiv:2104.13302 (2021)","DOI":"10.1109\/IJCNN52387.2021.9534316"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, D.: Multi-initialization meta-learning with domain adaptation. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1390\u20131394. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414554"},{"issue":"1","key":"35_CR6","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: An overview. IEEE Sig. Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Sig. Process. Mag."},{"key":"35_CR7","unstructured":"Ghasemipour, S.K.S., Zemel, R., Gu, S.: A divergence minimization perspective on imitation learning methods. In: Conference on Robot Learning, pp. 1259\u20131277. PMLR (2020)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Guo, T., et al.: On positive-unlabeled classification in GAN . In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8385\u20138393 (2020)","DOI":"10.1109\/CVPR42600.2020.00841"},{"key":"35_CR9","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems 29 (NIPS 2016), pp. 4565\u20134573 (2016)"},{"key":"35_CR10","unstructured":"Kiryo, R., Niu, G., Plessis, M.C.d., Sugiyama, M.: Positive-unlabeled learning with non-negative risk estimator. arXiv preprint arXiv:1703.00593 (2017)"},{"key":"35_CR11","unstructured":"Lyu, J., Ma, X., Yan, J., Li, X.: Efficient continuous control with double actors and regularized critics. arXiv preprint arXiv:2106.03050 (2021)"},{"key":"35_CR12","unstructured":"Natarajan, N., Dhillon, I.S., Ravikumar, P., Tewari, A.: Learning with noisy labels. In: NIPS (2013)"},{"key":"35_CR13","unstructured":"Ng, A.Y., Russell, S.J., et al.: Algorithms for inverse reinforcement learning. In: ICML. vol. 1, p. 2 (2000)"},{"key":"35_CR14","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR15","unstructured":"Ross, S., Bagnell, D.: Efficient reductions for imitation learning. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 661\u2013668. JMLR Workshop and Conference Proceedings (2010)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Sasaki, F., Yamashina, R.: Behavioral cloning from noisy demonstrations. In: International Conference on Learning Representations (2020)","DOI":"10.1299\/jsmermd.2020.2A1-L11"},{"key":"35_CR17","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"35_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7676","key":"35_CR19","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1038\/550336a","volume":"550","author":"S Singh","year":"2017","unstructured":"Singh, S., Okun, A., Jackson, A.: Learning to play go from scratch. Nature 550(7676), 336\u2013337 (2017)","journal-title":"Nature"},{"key":"35_CR20","unstructured":"Tangkaratt, V., Charoenphakdee, N., Sugiyama, M.: Robust imitation learning from noisy demonstrations. arXiv preprint arXiv:2010.10181 (2020)"},{"key":"35_CR21","unstructured":"Tangkaratt, V., Han, B., Khan, M.E., Sugiyama, M.: Variational imitation learning with diverse-quality demonstrations. In: International Conference on Machine Learning, pp. 9407\u20139417. PMLR (2020)"},{"key":"35_CR22","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":"35_CR23","unstructured":"Valko, M., Ghavamzadeh, M., Lazaric, A.: Semi-supervised apprenticeship learning. In: European Workshop on Reinforcement Learning, pp. 131\u2013142. PMLR (2013)"},{"key":"35_CR24","unstructured":"Wu, Y.H., Charoenphakdee, N., Bao, H., Tangkaratt, V., Sugiyama, M.: Imitation learning from imperfect demonstration. In: International Conference on Machine Learning, pp. 6818\u20136827. PMLR (2019)"},{"issue":"5","key":"35_CR25","first-page":"888","volume":"15","author":"R Yang","year":"2020","unstructured":"Yang, R., Yan, J., Li, X.: Survey of sparse reward algorithms in reinforcement learning - theory and experiment. CAAI Trans. Intell. Syst. 15(5), 888\u2013899 (2020)","journal-title":"CAAI Trans. Intell. Syst."},{"key":"35_CR26","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K., et al.: Maximum entropy inverse reinforcement learning. In: AAAI, vol. 8, pp. 1433\u20131438. Chicago, IL, USA (2008)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92270-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:26:28Z","timestamp":1710257188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92270-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030922696","9783030922702"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92270-2_35","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 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}