{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:28:40Z","timestamp":1747974520462,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031138409"},{"type":"electronic","value":"9783031138416"}],"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\/978-3-031-13841-6_41","type":"book-chapter","created":{"date-parts":[[2022,8,9]],"date-time":"2022-08-09T14:04:51Z","timestamp":1660053891000},"page":"449-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Improved Off-Policy Actor-Critic Algorithm with\u00a0Historical Behaviors Reusing for\u00a0Robotic Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4218-7542","authenticated-orcid":false,"given":"Huaqing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,10]]},"reference":[{"unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning. GitHub Repository (2016)","key":"41_CR1"},{"key":"41_CR2","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1049\/iet-its.2019.0317","volume":"14","author":"J Duan","year":"2020","unstructured":"Duan, J., Li, S.E., Guan, Y., Sun, Q., et al.: Hierarchical reinforcement learning for self-driving decision-making without reliance on labelled driving data. IET Intell. Transp. Syst. 14, 297\u2013305 (2020)","journal-title":"IET Intell. Transp. Syst."},{"key":"41_CR3","doi-asserted-by":"publisher","first-page":"5876","DOI":"10.1109\/TVT.2020.2986005","volume":"69","author":"Y Fu","year":"2020","unstructured":"Fu, Y., Li, C., Yu, F.R., Luan, T.H., et al.: A decision-making strategy for vehicle autonomous breaking in emergency via deep reinforcement learning. IEEE Trans. Veh. Technol. 69, 5876\u20135888 (2020)","journal-title":"IEEE Trans. Veh. Technol."},{"unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596 (2018)","key":"41_CR4"},{"unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, pp. 1352\u20131361 (2017)","key":"41_CR5"},{"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, pp. 1861\u20131870 (2018)","key":"41_CR6"},{"unstructured":"Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv (2018)","key":"41_CR7"},{"key":"41_CR8","doi-asserted-by":"publisher","first-page":"5081","DOI":"10.1109\/LRA.2021.3068639","volume":"3","author":"D Hoeller","year":"2021","unstructured":"Hoeller, D., Wellhausen, L., Farshidian, F.: Learning a state representation and navigation in cluttered and dynamic environments. IEEE Rob. Autom. Lett. 3, 5081\u20135088 (2021)","journal-title":"IEEE Rob. Autom. Lett."},{"unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv (2015)","key":"41_CR9"},{"unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv (2013)","key":"41_CR10"},{"key":"41_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"7540","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., et al.: Human-level control through deep reinforcement learning. Nature 7540, 529\u2013533 (2015)","journal-title":"Nature"},{"unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021). http:\/\/jmlr.org\/papers\/v22\/20-1364.html","key":"41_CR12"},{"key":"41_CR13","first-page":"169","volume":"41","author":"RM Sakia","year":"1992","unstructured":"Sakia, R.M.: The box-cox transformation technique: a review. J. R. Stat. Soc.: Series D 41, 169\u2013178 (1992)","journal-title":"J. R. Stat. Soc.: Series D"},{"unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., et al.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)","key":"41_CR14"},{"unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv (2017)","key":"41_CR15"},{"doi-asserted-by":"crossref","unstructured":"Toussaint, M.: Robot trajectory optimization using approximate inference. In: International Conference on Machine Learning, pp. 1049\u20131056 (2009)","key":"41_CR16","DOI":"10.1145\/1553374.1553508"},{"key":"41_CR17","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M.: Grandmaster level in starcraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"41_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105201","volume":"196","author":"X Wu","year":"2020","unstructured":"Wu, X., Chen, H., Chen, C., Zhong, M., et al.: The autonomous navigation and obstacle avoidance for USVS with ANOA deep reinforcement learning method. Knowl. Based Syst. 196, 105201 (2020)","journal-title":"Knowl. Based Syst."},{"unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: AAAI Conference on Artificial Intelligence, pp. 1433\u20131438 (2008)","key":"41_CR19"}],"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\/978-3-031-13841-6_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T23:04:11Z","timestamp":1660604651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13841-6_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138409","9783031138416"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13841-6_41","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":"10 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)"}}]}}