{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T15:47:35Z","timestamp":1769356055957,"version":"3.49.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030893699","type":"print"},{"value":"9783030893705","type":"electronic"}],"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\/978-3-030-89370-5_3","type":"book-chapter","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:02:59Z","timestamp":1635728579000},"page":"32-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Diversity-Based Trajectory and Goal Selection with Hindsight Experience Replay"],"prefix":"10.1007","author":[{"given":"Tianhong","family":"Dai","sequence":"first","affiliation":[]},{"given":"Hengyan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Arulkumaran","sequence":"additional","affiliation":[]},{"given":"Guangyu","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Anil Anthony","family":"Bharath","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,1]]},"reference":[{"key":"3_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Neural Information Processing Systems (2017)"},{"issue":"1","key":"3_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364919887447","volume":"39","author":"OM Andrychowicz","year":"2020","unstructured":"Andrychowicz, O.M., et al.: Learning dexterous in-hand manipulation. Int. J. Robot. Res. 39(1), 3\u201320 (2020)","journal-title":"Int. J. Robot. Res."},{"issue":"6","key":"3_CR3","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 Signal Process. Mag. 34(6), 26\u201338 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"3_CR4","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv:1912.06680 (2019)"},{"key":"3_CR5","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"10","key":"3_CR6","doi-asserted-by":"publisher","first-page":"1742","DOI":"10.3390\/electronics9101742","volume":"9","author":"T Dai","year":"2020","unstructured":"Dai, T., Liu, H., Bharath, A.A.: Episodic self-imitation learning with hindsight. Electronics 9(10), 1742 (2020)","journal-title":"Electronics"},{"key":"3_CR7","unstructured":"Fang, M., Zhou, C., Shi, B., Gong, B., Xu, J., Zhang, T.: DHER: Hindsight experience replay for dynamic goals. In: International Conference on Learning Representations (2018)"},{"key":"3_CR8","unstructured":"Fang, M., Zhou, T., Du, Y., Han, L., Zhang, Z.: Curriculum-guided hindsight experience replay. In: Neural Information Processing Systems (2019)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Hong, K., Nenkova, A.: Improving the estimation of word importance for news multi-document summarization. In: Conference of the European Chapter of the Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/E14-1075"},{"key":"3_CR11","unstructured":"Kaelbling, L.P.: Learning to achieve goals. In: International Joint Conference on Artificial Intelligence (1993)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 1\u201318 (2021)","DOI":"10.1109\/TITS.2021.3054625"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Kulesza, A., Taskar, B.: k-DPPs: fixed-size determinantal point processes. In: International Conference on Machine Learning (2011)","DOI":"10.1561\/9781601986290"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Kulesza, A., et al.: Determinantal Point Processes for Machine Learning. Foundations and Trends in Machine Learning (2012)","DOI":"10.1561\/9781601986290"},{"key":"3_CR15","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17, 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR16","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: International Conference on Learning Representations (2016)"},{"key":"3_CR17","unstructured":"Liu, H., Trott, A., Socher, R., Xiong, C.: Competitive experience replay. In: International Conference on Learning Representations (2019)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., Todorovic, S.: Unsupervised video summarization with adversarial lstm networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.318"},{"key":"3_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"3_CR20","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Theory and application to reward shaping. In: International Conference on Machine Learning (1999)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Osogami, T., Raymond, R.: Determinantal reinforcement learning. In: AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33014659"},{"key":"3_CR22","unstructured":"Parker-Holder, J., Pacchiano, A., Choromanski, K.M., Roberts, S.J.: Effective diversity in population based reinforcement learning. In: Neural Information Processing Systems (2020)"},{"key":"3_CR23","unstructured":"Plappert, M., et al.: Multi-goal reinforcement learning: challenging robotics environments and request for research. arXiv:1802.09464 (2018)"},{"key":"3_CR24","unstructured":"Rauber, P., Ummadisingu, A., Mutz, F., Schmidhuber, J.: Hindsight policy gradients. In: International Conference on Learning Representations (2019)"},{"key":"3_CR25","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: International Conference on Machine Learning (2015)"},{"key":"3_CR26","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: International Conference on Learning Representations (2016)"},{"key":"3_CR27","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering Atari, go, chess and shogi by planning with a learned model. Nature 588, 604\u2013609 (2020)","journal-title":"Nature"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"3_CR29","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (2018)"},{"key":"3_CR30","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in Starcraft ii using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"3_CR31","unstructured":"Yang, Y., et al.: Multi-agent determinantal q-learning. In: International Conference on Machine Learning (2020)"},{"key":"3_CR32","unstructured":"Zhao, R., Tresp, V.: Energy-based hindsight experience prioritization. In: Conference on Robot Learning (2018)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89370-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:10:30Z","timestamp":1635729030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89370-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030893699","9783030893705"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89370-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"382","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":"93","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":"28","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":"24% - 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)"}}]}}