{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:00:24Z","timestamp":1778256024532,"version":"3.51.4"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031059353","type":"print"},{"value":"9783031059360","type":"electronic"}],"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\/978-3-031-05936-0_22","type":"book-chapter","created":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:07:09Z","timestamp":1652198829000},"page":"277-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hard Negative Sample Mining for\u00a0Contrastive Representation in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Qihang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dayang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8448-7845","authenticated-orcid":false,"given":"Yunlong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,11]]},"reference":[{"key":"22_CR1","unstructured":"Srinivas, A., Laskin, M., Abbeel, P.: CURL: contrastive unsupervised representations for reinforcement learning (2020)"},{"key":"22_CR2","unstructured":"Kaiser, L., et al.: Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 (2019)"},{"key":"22_CR3","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"key":"22_CR4","unstructured":"Mutti, M., Pratissoli, L., Restelli, M.: A policy gradient method for task-agnostic exploration (2020)"},{"key":"22_CR5","unstructured":"Veeriah, V., Oh, J., Singh, S.: Many-goals reinforcement learning. arXiv preprint arXiv:1806.09605 (2018)"},{"key":"22_CR6","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"22_CR7","unstructured":"Talvitie, E.: Model regularization for stable sample rollouts. In: UAI (2014)"},{"key":"22_CR8","unstructured":"Racani\u00e8re, S., et al.: Imagination-augmented agents for deep reinforcement learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (2017)"},{"key":"22_CR9","unstructured":"Tassa, Y., et al.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"22_CR10","unstructured":"Yarats, D., et al.: Improving sample efficiency in model-free reinforcement learning from images. arXiv preprint arXiv:1910.01741 (2019)"},{"key":"22_CR11","unstructured":"Yarats, D., et al.: Reinforcement learning with prototypical representations. arXiv preprint arXiv:2102.11271 (2021)"},{"key":"22_CR12","unstructured":"Chen, X., et al.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., et al.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","DOI":"10.1613\/jair.3912"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Unsupervised feature learning via non-parametric instance-level discrimination. arXiv preprint arXiv:1805.01978 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"22_CR15","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"22_CR16","unstructured":"Hafner, D., et al.: Dream to control: learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603 (2019)"},{"key":"22_CR17","unstructured":"Lee, K.-H., et al.: Predictive information accelerates learning in RL. arXiv preprint arXiv:2007.12401 (2020)"},{"key":"22_CR18","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"22_CR19","unstructured":"Robinson, J., et al.: Contrastive learning with hard negative samples. arXiv preprint arXiv:2010.04592 (2020)"},{"key":"22_CR20","unstructured":"Chuang, C.-Y., et al.: Debiased contrastive learning. arXiv preprint arXiv:2007.00224 (2020)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Le-Khac, P.H., Healy, G., Smeaton, A.F.: Contrastive representation learning: a framework and review. IEEE Access 8, 193907\u2013193934(2020)","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Suh, Y., et al.: Stochastic class-based hard example mining for deep metric learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00742"},{"key":"22_CR23","unstructured":"Zhu, J., et al.: Masked contrastive representation learning for reinforcement learning. arXiv preprint arXiv:2010.07470 (2020)"},{"key":"22_CR24","unstructured":"Kostrikov, I., Yarats, D., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. arXiv preprint arXiv:2004.13649 (2020)"},{"key":"22_CR25","unstructured":"Liu, G., et al.: Return-based contrastive representation learning for reinforcement learning. arXiv preprint arXiv:2102.10960 (2021)"},{"key":"22_CR26","unstructured":"Laskin, M., et al.: Reinforcement learning with augmented data. arXiv preprint arXiv:2004.14990 (2020)"},{"key":"22_CR27","unstructured":"Yarats, D., et al.: Mastering visual continuous control: improved data-augmented reinforcement learning. arXiv preprint arXiv:2107.09645 (2021)"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, W.B., Lindenstrauss, J.: Extensions of Lipschitz mappings into a Hilbert space 26. Contemp. Math. 26, 28 (1984)","DOI":"10.1090\/conm\/026\/737400"},{"key":"22_CR29","unstructured":"Blundell, C., et al.: Model-free episodic control. arXiv preprint arXiv:1606.04460 (2016)"},{"key":"22_CR30","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"22_CR33","unstructured":"Bachman, P., Devon Hjelm, R., Buchwalter, W.: Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019)"},{"key":"22_CR34","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings (2010)"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Wang, F., Liu, H.: Understanding the behaviour of contrastive loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., et al.: Sampling matters in deep embedding learning. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.309"},{"key":"22_CR37","unstructured":"Yan, W., et al.: Learning predictive representations for deformable objects using contrastive estimation. arXiv preprint arXiv:2003.05436 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-05936-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T16:05:59Z","timestamp":1654531559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-05936-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031059353","9783031059360"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-05936-0_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","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":"16 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pakdd.net\/index.html","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":"558","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":"121","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":"22% - 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":"3.75","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":"6.45","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)"}}]}}