{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:56:14Z","timestamp":1743094574770,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031402913"},{"type":"electronic","value":"9783031402920"}],"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\/978-3-031-40292-0_29","type":"book-chapter","created":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T23:02:48Z","timestamp":1691535768000},"page":"356-365","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task Inference for\u00a0Offline Meta Reinforcement Learning via\u00a0Latent Shared Knowledge"],"prefix":"10.1007","author":[{"given":"Ying","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Cong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,9]]},"reference":[{"key":"29_CR1","unstructured":"Beck, J., Vuorio, R., Liu, E.Z., et al.: A survey of meta-reinforcement learning. arXiv preprint arXiv:2301.08028 (2023)"},{"key":"29_CR2","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., et al.: Domain separation networks. In: NeurIPS, vol. 29 (2016)"},{"key":"29_CR3","unstructured":"Dorfman, R., Shenfeld, I., Tamar, A.: Offline meta reinforcement learning-identifiability challenges and effective data collection strategies. In: NeurIPS, vol. 34, pp. 4607\u20134618 (2021)"},{"key":"29_CR4","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., et al.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML, pp. 1861\u20131870. PMLR (2018)"},{"key":"29_CR5","unstructured":"Humplik, J., Galashov, A., Hasenclever, L., et al.: Meta reinforcement learning as task inference. arXiv preprint arXiv:1905.06424 (2019)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Johannink, T., Bahl, S., Nair, A., et al.: Residual reinforcement learning for robot control. In: ICRA, pp. 6023\u20136029. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794127"},{"issue":"6","key":"29_CR7","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran, B.R., Sobh, I., Talpaert, V., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"29_CR8","unstructured":"Levine, S., Kumar, A., Tucker, G., et al.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"29_CR9","unstructured":"Li, L., Huang, Y., Chen, M., et al.: Provably improved context-based offline meta-RL with attention and contrastive learning. arXiv preprint arXiv:2102.10774 (2021)"},{"key":"29_CR10","unstructured":"Li, L., Yang, R., Luo, D.: Focal: efficient fully-offline meta-reinforcement learning via distance metric learning and behavior regularization. arXiv preprint arXiv:2010.01112 (2020)"},{"key":"29_CR11","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"issue":"7540","key":"29_CR12","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., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"29_CR13","unstructured":"Nagabandi, A., Clavera, I., Liu, S., et al.: Learning to adapt in dynamic, real-world environments through meta-reinforcement learning. arXiv preprint arXiv:1803.11347 (2018)"},{"key":"29_CR14","unstructured":"Rakelly, K., Zhou, A., Finn, C., et al.: Efficient off-policy meta-reinforcement learning via probabilistic context variables. In: ICML, pp. 5331\u20135340. PMLR (2019)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Ye, D., Liu, Z., Sun, M., et al.: Mastering complex control in MOBA games with deep reinforcement learning. In: AAAI, vol. 34, pp. 6672\u20136679 (2020)","DOI":"10.1609\/aaai.v34i04.6144"},{"issue":"1","key":"29_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3477600","volume":"55","author":"C Yu","year":"2021","unstructured":"Yu, C., Liu, J., Nemati, S., Yin, G.: Reinforcement learning in healthcare: a survey. ACM Comput. Surv. (CSUR) 55(1), 1\u201336 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"29_CR17","unstructured":"Yuan, H., Lu, Z.: Robust task representations for offline meta-reinforcement learning via contrastive learning. In: ICML, pp. 25747\u201325759. PMLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40292-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T23:08:08Z","timestamp":1691536088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40292-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031402913","9783031402920"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40292-0_29","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":"9 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ksem2023.conferences.academy\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"395","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":"114","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":"30","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":"29% - 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":"2,5","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)"}}]}}