{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:26:25Z","timestamp":1742912785139,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030873608"},{"type":"electronic","value":"9783030873615"}],"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\/978-3-030-87361-5_15","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T23:54:11Z","timestamp":1632959651000},"page":"182-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hindsight Curriculum Generation Based Multi-Goal Experience Replay"],"prefix":"10.1007","author":[{"given":"Xiaoyun","family":"Feng","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484 (2016)","journal-title":"Nature"},{"issue":"7676","key":"15_CR2","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(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"15_CR4","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2\u20134 May 2016, Conference Track Proceedings (2016)"},{"key":"15_CR5","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017)"},{"key":"15_CR6","unstructured":"Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR7","unstructured":"Plappert, M., et al.: Multi-goal reinforcement learning: challenging robotics environments and request for research. CoRR abs\/1802.09464 (2018)"},{"key":"15_CR8","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"},{"key":"15_CR9","unstructured":"Popov, I., et al.: Data-efficient deep reinforcement learning for dexterous manipulation. CoRR abs\/1704.03073 (2017)"},{"key":"15_CR10","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"15_CR11","unstructured":"Zhao, R., Tresp, V.: Energy-based hindsight experience prioritization. In: Proceedings of The 2nd Conference on Robot Learning. Proceedings of Machine Learning Research, vol. 87, pp. 113\u2013122. PMLR, 29\u201331 Oct 2018"},{"key":"15_CR12","unstructured":"Fang, M., Zhou, T., Du, Y., Han, L., Zhang, Z.: Curriculum-guided hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"15_CR13","unstructured":"Zhao, R., Sun, X., Tresp, V.: Maximum entropy-regularized multi-goal reinforcement learning. In: Proceedings of the 23rd International Conference on Machine Learning (2019)"},{"key":"15_CR14","unstructured":"Sutton, R.S., Barto., A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT press, Cambridge (2018)"},{"key":"15_CR15","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: ICML, pp. 1312\u20131320 (2015)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"15_CR17","unstructured":"Pong, V., Gu, S., Dalal, M., Levine, S.: Temporal difference models: model-free deep RL for model-based control. CoRR abs\/1802.09081 (2018)"},{"key":"15_CR18","unstructured":"Rauber, P., Ummadisingu, A., Mutz, F., Schmidhuber, J.: Hindsight policy gradients. In: International Conference on Learning Representations (2019)"},{"key":"15_CR19","unstructured":"Li, A., Pinto, L., Abbeel, P.: Generalized hindsight for reinforcement learning. ArXiv:abs\/2002.11708 (2020)"},{"key":"15_CR20","unstructured":"Ren, Z., Dong, K., Zhou, Y., Liu, Q., Peng, J.: Exploration via hindsight goal generation. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"15_CR21","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 (2019)"},{"key":"15_CR22","unstructured":"Riedmiller, M., et al.: Learning by playing - solving sparse reward tasks from scratch (2018)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"\u015eim\u015fek, O., Barto, A.G.: An intrinsic reward mechanism for efficient exploration. In: Proceedings of the 23rd International Conference on Machine Learning. pp. 833\u2013840. ICML 2006. ACM, New York (2006)","DOI":"10.1145\/1143844.1143949"},{"issue":"3","key":"15_CR24","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3102\/00346543064003363","volume":"64","author":"J Cameron","year":"1994","unstructured":"Cameron, J., Pierce, W.D.: Reinforcement, reward, and intrinsic motivation: a meta-analysis. Rev. Educ. Res. 64(3), 363\u2013423 (1994)","journal-title":"Rev. Educ. Res."},{"key":"15_CR25","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1515\u20131528. PMLR, Stockholmsm\u00e4ssan, 10\u201315 Jul 2018"},{"key":"15_CR26","unstructured":"Pong, V.H., Dalal, M., Lin, S., Nair, A., Bahl, S., Levine, S.: Skew-fit: state-covering self-supervised reinforcement learning. CoRR abs\/1903.03698 (2019)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87361-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:04:18Z","timestamp":1632960258000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87361-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030873608","9783030873615"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87361-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2021.csig.org.cn\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"421","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":"198","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":"47% - 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":"3","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)"}},{"value":"Conference was postponed due to the COVID19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}