{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:43:00Z","timestamp":1765546980517,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031138430"},{"type":"electronic","value":"9783031138447"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-13844-7_58","type":"book-chapter","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T18:18:24Z","timestamp":1659550704000},"page":"627-636","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Mixline: A Hybrid Reinforcement Learning Framework for\u00a0Long-Horizon Bimanual Coffee Stirring Task"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,4]]},"reference":[{"issue":"6","key":"58_CR1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Sign. Process. Mag. 34(6), 26\u201338 (2017). https:\/\/doi.org\/10.1109\/MSP.2017.2743240","journal-title":"IEEE Sign. Process. Mag."},{"key":"58_CR2","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-981-15-4095-0_2","volume-title":"Deep Reinforcement Learning","author":"Z Ding","year":"2020","unstructured":"Ding, Z., Huang, Y., Yuan, H., Dong, H.: Introduction to reinforcement learning. In: Dong, H., Ding, Z., Zhang, S. (eds.) Deep Reinforcement Learning, pp. 47\u2013123. Springer, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-4095-0_2"},{"key":"58_CR3","unstructured":"Zhang, M., Jian, P., Wu, Y., Xu, H., Wang, X.: Disentangled attention as intrinsic regularization for bimanual multi-object manipulation. arXiv e-prints, pp. arXiv-2106 (2021)"},{"key":"58_CR4","doi-asserted-by":"crossref","unstructured":"Chitnis, R., Tulsiani, S., Gupta, S., Gupta, A.: Efficient bimanual manipulation using learned task schemas. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 1149\u20131155. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"58_CR5","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"58_CR6","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"issue":"4","key":"58_CR7","doi-asserted-by":"publisher","first-page":"1816","DOI":"10.3390\/app11041816","volume":"11","author":"L Liu","year":"2021","unstructured":"Liu, L., Liu, Q., Song, Y., Pang, B., Yuan, X., Xu, Q.: A collaborative control method of dual-arm robots based on deep reinforcement learning. Appl. Sci. 11(4), 1816 (2021)","journal-title":"Appl. Sci."},{"key":"58_CR8","doi-asserted-by":"crossref","unstructured":"Chiu, Z.Y., Richter, F., Funk, E.K., Orosco, R.K., Yip, M.C.: Bimanual regrasping for suture needles using reinforcement learning for rapid motion planning. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 7737\u20137743. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561673"},{"key":"58_CR9","doi-asserted-by":"crossref","unstructured":"Rajeswaran, A., et al.: Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. arXiv preprint arXiv:1709.10087 (2017)","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"58_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104165","volume":"100","author":"J Liu","year":"2021","unstructured":"Liu, J., Zhang, H., Fu, Z., Wang, Y.: Learning scalable multi-agent coordination by spatial differentiation for traffic signal control. Eng. Appl. Artif. Intell. 100, 104165 (2021)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"58_CR11","doi-asserted-by":"crossref","unstructured":"Cabi, S., et al.: Scaling data-driven robotics with reward sketching and batch reinforcement learning. arXiv preprint arXiv:1909.12200 (2019)","DOI":"10.15607\/RSS.2020.XVI.076"},{"key":"58_CR12","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":"58_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. Handbook of Reinforcement Learning and Control, pp. 321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"58_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Robot cooking with stir-fry: bimanual non-prehensile manipulation of semi-fluid objects. IEEE Robot. Autom. Lett. 7(2), 5159\u20135166 (2022)","DOI":"10.1109\/LRA.2022.3153728"},{"issue":"2","key":"58_CR15","doi-asserted-by":"publisher","first-page":"4917","DOI":"10.1109\/LRA.2022.3152974","volume":"7","author":"Z Dong","year":"2022","unstructured":"Dong, Z., Li, Z., Yan, Y., Calinon, S., Chen, F.: Passive bimanual skills learning from demonstration with motion graph attention networks. IEEE Robot. Autom. Lett. 7(2), 4917\u20134923 (2022). https:\/\/doi.org\/10.1109\/LRA.2022.3152974","journal-title":"IEEE Robot. Autom. Lett."},{"key":"58_CR16","unstructured":"Makoviychuk, V., et al.: Isaac Gym: high performance GPU-based physics simulation for robot learning (2021)"},{"key":"58_CR17","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"issue":"1","key":"58_CR18","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/LRA.2016.2517147","volume":"1","author":"W Wan","year":"2016","unstructured":"Wan, W., Harada, K.: Developing and comparing single-arm and dual-arm regrasp. IEEE Robot. Autom. Lett. 1(1), 243\u2013250 (2016)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"58_CR19","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to reinforcement learning (1998)"},{"key":"58_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"58_CR21","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":"58_CR22","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":"58_CR23","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning (ICML) (2018)"},{"key":"58_CR24","unstructured":"Liu, J., et al.: Efficient reinforcement learning control for continuum robots based on inexplicit prior knowledge. arXiv preprint arXiv:2002.11573 (2020)"},{"key":"58_CR25","unstructured":"Yadan, O.: Hydra - a framework for elegantly configuring complex applications. Github (2019). https:\/\/github.com\/facebookresearch\/hydra"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13844-7_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T23:20:01Z","timestamp":1660605601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13844-7_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138430","9783031138447"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13844-7_58","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icira2022.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"442","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":"284","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":"64% - 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":"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)"}}]}}