{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:29:22Z","timestamp":1762342162561,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434204"},{"type":"electronic","value":"9783031434211"}],"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\/978-3-031-43421-1_33","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"556-572","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Salient Patch Selection for\u00a0Data-Efficient Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5391-5112","authenticated-orcid":false,"given":"Zhaohui","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2008-4569","authenticated-orcid":false,"given":"Paul","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"33_CR1","unstructured":"Agnew, W., Domingos, P.: Unsupervised object-level deep reinforcement learning. In: NeurIPS Workshop on Deep RL (2018)"},{"key":"33_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"33_CR3","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: ICML (2017)"},{"key":"33_CR4","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"33_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"33_CR6","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. In: ICLR (2018)"},{"key":"33_CR7","unstructured":"Goel, V., Weng, J., Poupart, P.: Unsupervised video object segmentation for deep reinforcement learning. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"33_CR8","unstructured":"Gopalakrishnan, A., van Steenkiste, S., Schmidhuber, J.: Unsupervised object keypoint learning using local spatial predictability. In: International Conference on Learning Representations (2020)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Goul\u00e3o, M., Oliveira, A.L.: Pretraining the vision transformer using self-supervised methods for vision based deep reinforcement learning (2022)","DOI":"10.3233\/FAIA230359"},{"key":"33_CR10","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML (2018)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Thirty-second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"33_CR15","unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks. In: International Conference on Learning Representations (2017)"},{"key":"33_CR16","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"33_CR17","unstructured":"Kaiser, \u0141., et al.: Model based reinforcement learning for Atari. In: International Conference on Learning Representations (2019)"},{"key":"33_CR18","unstructured":"Kalantari, A.A., Amini, M., Chandar, S., Precup, D.: Improving sample efficiency of value based models using attention and vision transformers. arXiv preprint arXiv:2202.00710 (2022)"},{"key":"33_CR19","unstructured":"Kielak, K.P.: Do recent advancements in model-based deep reinforcement learning really improve data efficiency? In: ICLR, p. 6 (2020). https:\/\/openreview.net\/forum?id=Bke9u1HFwB"},{"key":"33_CR20","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.ejor.2003.06.010","volume":"158","author":"M Kostreva","year":"2004","unstructured":"Kostreva, M., Ogryczak, W., Wierzbicki, A.: Equitable aggregations and multiple criteria analysis. Eur. J. Operat. Res. 158, 362\u2013367 (2004)","journal-title":"Eur. J. Operat. Res."},{"key":"33_CR21","unstructured":"Kulkarni, T.D., et al.: Unsupervised learning of object keypoints for perception and control. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"33_CR22","unstructured":"Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., Srinivas, A.: Reinforcement learning with augmented data. In: NeurIPS (2020)"},{"key":"33_CR23","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. In: JMLR (2016)"},{"key":"33_CR24","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Lin, Y., Huang, J., Zimmer, M., Guan, Y., Rojas, J., Weng, P.: Invariant transform experience replay: Data augmentation for deep reinforcement learning. IEEE Robot. Autom. Lett. IROS PP, 1 (2020)","DOI":"10.1109\/LRA.2020.3013937"},{"key":"33_CR26","unstructured":"Manuelli, L., Li, Y., Florence, P., Tedrake, R.: Keypoints into the future: self-supervised correspondence in model-based reinforcement learning. In: CoRL (2020)"},{"key":"33_CR27","unstructured":"Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K.P., Lee, H.: Unsupervised learning of object structure and dynamics from videos. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"33_CR29","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. In: International Conference on Learning Representations (2018)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Puterman, M.: Markov decision processes: discrete stochastic dynamic programming. Wiley (1994)","DOI":"10.1002\/9780470316887"},{"key":"33_CR31","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: ICLR (2016)"},{"key":"33_CR32","unstructured":"Seo, Y., et al.: Masked world models for visual control. In: 6th Annual Conference on Robot Learning (2022)"},{"key":"33_CR33","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: an introduction. MIT Press (2018)"},{"key":"33_CR34","unstructured":"Tao, T., Reda, D., van de Panne, M.: Evaluating vision transformer methods for deep reinforcement learning from pixels (2022)"},{"key":"33_CR35","unstructured":"Van Hasselt, H.P., Hessel, M., Aslanides, J.: When to use parametric models in reinforcement learning? In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"33_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"33_CR37","unstructured":"Wang, T., et al.: Benchmarking model-based reinforcement learning (2019)"},{"key":"33_CR38","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. In: ICML (2016)"},{"key":"33_CR39","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. In: International Conference on Machine Learning, pp. 10524\u201310533. PMLR (2020)"},{"key":"33_CR40","unstructured":"Yarats, D., Kostrikov, I., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=GY6-6sTvGaf"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Yarats, D., Zhang, A., Kostrikov, I., Amos, B., Pineau, J., Fergus, R.: Improving sample efficiency in model-free reinforcement learning from images. In: AAAI (2020)","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"33_CR42","unstructured":"Zadaianchuk, A., Seitzer, M., Martius, G.: Self-supervised visual reinforcement learning with object-centric representations. In: International Conference on Learning Representations (2021)"},{"key":"33_CR43","unstructured":"Zambaldi, V., et al.: Deep reinforcement learning with relational inductive biases. In: International conference on learning representations (2018)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43421-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T23:11:45Z","timestamp":1703200305000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43421-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434204","9783031434211"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43421-1_33","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":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","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":"829","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":"196","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":"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":"3.63","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":"4.5","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)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","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)"}}]}}