{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:06Z","timestamp":1742914086551,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442391"},{"type":"electronic","value":"9783031442407"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44240-7_21","type":"book-chapter","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T22:01:45Z","timestamp":1695160905000},"page":"212-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised State Representation Learning in Partially Observable Atari Games"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8867-9104","authenticated-orcid":false,"given":"Li","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6331-702X","authenticated-orcid":false,"given":"Morten","family":"Goodwin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7591-1659","authenticated-orcid":false,"given":"Anis","family":"Yazidi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8371-927X","authenticated-orcid":false,"given":"Paal","family":"Engelstad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"21_CR1","unstructured":"Anand, A., Racah, E., Ozair, S., Bengio, Y., C\u00f4t\u00e9, M.A., Hjelm, R.D.: Unsupervised state representation learning in atari. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"21_CR2","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355 (2018)"},{"key":"21_CR3","unstructured":"Cassandra, A.R., Kaelbling, L.P., Littman, M.L.: Acting optimally in partially observable stochastic domains. In: AAAI, vol. 94, pp. 1023\u20131028 (1994)"},{"key":"21_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"21_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Doersch, C., Zisserman, A.: Multi-task self-supervised visual learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2051\u20132060 (2017)","DOI":"10.1109\/ICCV.2017.226"},{"key":"21_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR9","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: DRAW: a recurrent neural network for image generation. In: International Conference on Machine Learning, pp. 1462\u20131471. PMLR (2015)"},{"key":"21_CR10","unstructured":"Guo, Z.D., et al.: Bootstrap latent-predictive representations for multitask reinforcement learning. In: International Conference on Machine Learning, pp. 3875\u20133886. PMLR (2020)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"21_CR12","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"issue":"3","key":"21_CR13","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10514-015-9459-7","volume":"39","author":"R Jonschkowski","year":"2015","unstructured":"Jonschkowski, R., Brock, O.: Learning state representations with robotic priors. Auton. Robot. 39(3), 407\u2013428 (2015). https:\/\/doi.org\/10.1007\/s10514-015-9459-7","journal-title":"Auton. Robot."},{"key":"21_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1920\u20131929 (2019)","DOI":"10.1109\/CVPR.2019.00202"},{"key":"21_CR16","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: CURL: contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning, pp. 5639\u20135650. PMLR (2020)"},{"key":"21_CR17","first-page":"11890","volume":"33","author":"KH Lee","year":"2020","unstructured":"Lee, K.H., et al.: Predictive information accelerates learning in RL. Adv. Neural. Inf. Process. Syst. 33, 11890\u201311901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR18","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.neunet.2018.07.006","volume":"108","author":"T Lesort","year":"2018","unstructured":"Lesort, T., D\u00edaz-Rodr\u00edguez, N., Goudou, J.F., Filliat, D.: State representation learning for control: an overview. Neural Netw. 108, 379\u2013392 (2018)","journal-title":"Neural Netw."},{"key":"21_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning (2013)"},{"key":"21_CR20","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR21","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","volume":"2","author":"ML Puterman","year":"1990","unstructured":"Puterman, M.L.: Markov decision processes. Handbooks Oper. Res. Management Sci. 2, 331\u2013434 (1990)","journal-title":"Handbooks Oper. Res. Management Sci."},{"key":"21_CR22","unstructured":"Stooke, A., Lee, K., Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, pp. 9870\u20139879. PMLR (2021)"},{"key":"21_CR23","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Taylor, L.N., Whalen, Z.: Playing the Past: History and Nostalgia in Video Games. JSTOR (2008)","DOI":"10.2307\/j.ctv16759mn.4"},{"key":"21_CR25","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9446\u20139454 (2018)"},{"issue":"3\u20134","key":"21_CR26","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"3","key":"21_CR27","first-page":"3421","volume":"45","author":"J Zhu","year":"2022","unstructured":"Zhu, J., et al.: Masked contrastive representation learning for reinforcement learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3421\u20133433 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Analysis of Images and Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44240-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T22:06:50Z","timestamp":1695161210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44240-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442391","9783031442407"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44240-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"20 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Analysis of Images and Patterns","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cyprusconferences.org\/caip2023\/","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":"https:\/\/www.easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"54","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":"81% - 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":"2.06","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":"2.09","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}