{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:10:27Z","timestamp":1771261827230,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781124","type":"print"},{"value":"9783031781131","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78113-1_23","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:00:44Z","timestamp":1733245244000},"page":"346-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Goal-Driven Transformer for Robot Behavior Learning from Play Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6448-003X","authenticated-orcid":false,"given":"Congcong","family":"Wen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8016-8772","authenticated-orcid":false,"given":"Jiazhao","family":"Liang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-7966","authenticated-orcid":false,"given":"Shuaihang","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9131-5854","authenticated-orcid":false,"given":"Hao","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9119-6114","authenticated-orcid":false,"given":"Yu","family":"Hao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0190-969X","authenticated-orcid":false,"given":"Hui","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7305-1915","authenticated-orcid":false,"given":"Yu-Shen","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-3883","authenticated-orcid":false,"given":"Yi","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"issue":"5","key":"23_CR1","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469\u2013483 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Arunachalam, S.P., Silwal, S., Evans, B., Pinto, L.: Dexterous imitation made easy: A learning-based framework for efficient dexterous manipulation. In: 2023 ieee international conference on robotics and automation (icra). pp. 5954\u20135961. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"23_CR3","unstructured":"Cui, Z.J., Wang, Y., Muhammad, N., Pinto, L., et\u00a0al.: From play to policy: Conditional behavior generation from uncurated robot data. arXiv preprint arXiv:2210.10047 (2022)"},{"key":"23_CR4","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"23_CR5","unstructured":"Emmons, S., Eysenbach, B., Kostrikov, I., Levine, S.: Rvs: What is essential for offline rl via supervised learning? arXiv preprint arXiv:2112.10751 (2021)"},{"key":"23_CR6","unstructured":"Florence, P., et al.: Implicit behavioral cloning. In: Conference on Robot Learning. pp. 158\u2013168. PMLR (2022)"},{"key":"23_CR7","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)"},{"key":"23_CR8","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International conference on machine learning. pp. 1587\u20131596. PMLR (2018)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision. pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"23_CR10","unstructured":"Gupta, A., Kumar, V., Lynch, C., Levine, S., Hausman, K.: Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. arXiv preprint arXiv:1910.11956 (2019)"},{"key":"23_CR11","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)"},{"key":"23_CR12","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"23_CR13","unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy q-learning via bootstrapping error reduction. Advances in Neural Information Processing Systems 32 (2019)"},{"key":"23_CR14","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR16","unstructured":"Lynch, C., Khansari, M., Xiao, T., Kumar, V., Tompson, J., Levine, S., Sermanet, P.: Learning latent plans from play. In: Conference on robot learning. pp. 1113\u20131132. PMLR (2020)"},{"key":"23_CR17","unstructured":"Ma, Y.J., Yan, J., Jayaraman, D., Bastani, O.: How far i\u2019ll go: Offline goal-conditioned reinforcement learning via $$ f $$-advantage regression. arXiv preprint arXiv:2206.03023 (2022)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Mandlekar, A., Xu, D., Mart\u00edn-Mart\u00edn, R., Savarese, S., Fei-Fei, L.: Learning to generalize across long-horizon tasks from human demonstrations. arXiv preprint arXiv:2003.06085 (2020)","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"23_CR19","unstructured":"Mandlekar, A., Zhu, Y., Garg, A., Booher, J., Spero, M., Tung, A., Gao, J., Emmons, J., Gupta, A., Orbay, E., et\u00a0al.: Roboturk: A crowdsourcing platform for robotic skill learning through imitation. In: Conference on Robot Learning. pp. 879\u2013893. PMLR (2018)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Pari, J., Shafiullah, N.M., Arunachalam, S.P., Pinto, L.: The surprising effectiveness of representation learning for visual imitation. arXiv preprint arXiv:2112.01511 (2021)","DOI":"10.15607\/RSS.2022.XVIII.010"},{"issue":"4","key":"23_CR21","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Van de Panne, M.: Deepmimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Transactions On Graphics (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"23_CR22","unstructured":"Pomerleau, D.A.: Alvinn: An autonomous land vehicle in a neural network. Advances in neural information processing systems 1 (1988)"},{"key":"23_CR23","first-page":"22955","volume":"35","author":"NM Shafiullah","year":"2022","unstructured":"Shafiullah, N.M., Cui, Z., Altanzaya, A.A., Pinto, L.: Behavior transformers: Cloning $$ k $$ modes with one stone. Adv. Neural. Inf. Process. Syst. 35, 22955\u201322968 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Behavioral cloning from observation. arXiv preprint arXiv:1805.01954 (2018)","DOI":"10.24963\/ijcai.2018\/687"},{"key":"23_CR25","unstructured":"Yang, R., et al.: Rethinking goal-conditioned supervised learning and its connection to offline rl. arXiv preprint arXiv:2202.04478 (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:06:53Z","timestamp":1733245613000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}