{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:07:05Z","timestamp":1743052025578,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"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_62","type":"book-chapter","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T18:18:24Z","timestamp":1659550704000},"page":"669-680","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-objective RL with\u00a0Preference Exploration"],"prefix":"10.1007","author":[{"given":"Wei","family":"Xi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,4]]},"reference":[{"key":"62_CR1","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"62_CR2","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"62_CR3","doi-asserted-by":"crossref","unstructured":"Hayes, C.F., R\u0103dulescu, R., Bargiacchi, E., et al.: A practical guide to multi-objective reinforcement learning and planning. arXiv preprint arXiv:2103.09568 (2021)","DOI":"10.1007\/s10458-022-09552-y"},{"key":"62_CR4","first-page":"17443","volume":"33","author":"WM Czarnecki","year":"2020","unstructured":"Czarnecki, W.M., Gidel, G., Tracey, B., et al.: Real world games look like spinning tops. Adv. Neural. Inf. Process. Syst. 33, 17443\u201317454 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"62_CR5","first-page":"1","volume":"11","author":"DM Roijers","year":"2017","unstructured":"Roijers, D.M., Whiteson, S.: Multi-objective decision making. Synth. Lect. Artif. Intell. Mach. Learn. 11(1), 1\u2013129 (2017)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"62_CR6","doi-asserted-by":"crossref","unstructured":"Shen, R., Zheng, Y., Hao, J., et al.: Generating behavior-diverse game AIs with evolutionary multi-objective deep reinforcement learning. In: IJCAI, pp. 3371\u20133377 (2020)","DOI":"10.24963\/ijcai.2020\/466"},{"key":"62_CR7","unstructured":"Friedman, E., Fontaine, F.: Generalizing across multi-objective reward functions in deep reinforcement learning. arXiv preprint arXiv:1809.06364 (2018)"},{"key":"62_CR8","unstructured":"Andrychowicz, M., Wolski, F., Ray, A., et al.: Hindsight experience replay. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"62_CR9","unstructured":"Abels, A., Roijers, D., Lenaerts, T., et al.: Dynamic weights in multi-objective deep reinforcement learning. In: International Conference on Machine Learning. PMLR, pp. 11\u201320 (2019)"},{"key":"62_CR10","unstructured":"Yang R, Sun X, Narasimhan K. A generalized algorithm for multi-objective reinforcement learning and policy adaptation[J]. Advances in Neural Information Processing Systems, 2019, 32"},{"key":"62_CR11","doi-asserted-by":"crossref","unstructured":"Wu, Z., Li, K., Zhao, E., et al.: L2e: learning to exploit your opponent. arXiv preprint arXiv:2102.09381 (2021)","DOI":"10.1109\/IJCNN55064.2022.9892077"},{"key":"62_CR12","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., et al.: Diversity is all you need: learning skills without a reward function. arXiv preprint arXiv:1802.06070 (2018)"},{"key":"62_CR13","unstructured":"Schaul, T., Quan, J., Antonoglou, I., et al.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"62_CR14","doi-asserted-by":"crossref","unstructured":"Vamplew, P., Yearwood, J., Dazeley, R., et al.: On the limitations of scalarisation for multi-objective reinforcement learning of pareto fronts. In: Australasian Joint Conference on Artificial Intelligence. Springer, Berlin, Heidelberg, pp. 372\u2013378 (2008)","DOI":"10.1007\/978-3-540-89378-3_37"},{"issue":"8","key":"62_CR15","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: An analysis of model-based interval estimation for Markov decision processes. J. Comput. Syst. Sci. 74(8), 1309\u20131331 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"62_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"62_CR17","unstructured":"G\u00e1bor, Z., Kalm\u00e1r, Z., Szepesv\u00e1ri, C.: Multi-criteria reinforcement learning. In: ICML, vol. 98, pp. 197\u2013205 (1998)"}],"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_62","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T15:05:24Z","timestamp":1676300724000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13844-7_62"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138430","9783031138447"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13844-7_62","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)"}}]}}