{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:25:05Z","timestamp":1743006305533,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031205026"},{"type":"electronic","value":"9783031205033"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20503-3_7","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"81-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Dictionary Learning-Based Reinforcement Learning with Non-convex Sparsity Regularizer"],"prefix":"10.1007","author":[{"given":"Haoli","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenini","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengli","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"issue":"8","key":"7_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR2","unstructured":"Fan, J., Wang, Z., Xie, Y., Yang, Z.: A theoretical analysis of deep q-learning. In: Proceedings of the 2nd Conference on Learning for Dynamics and Control, pp. 486\u2013489. PMLR (2020)"},{"key":"7_CR3","unstructured":"Hernandez-Garcia, J.F., Sutton, R.S.: Learning sparse representations incrementally in deep reinforcement learning. arXiv preprint arXiv:1912.04002 (2019)"},{"key":"7_CR4","unstructured":"Hoyer, P.O.: Non-negative matrix factorization with sparseness constraints. J. Mach. Learn. Res. 5(9) (2004)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Kim, S., Asadi, K., Littman, M., Konidaris, G.: Deepmellow: removing the need for a target network in deep q-learning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/379"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Le, L., Kumaraswamy, R., White, M.: Learning sparse representations in reinforcement learning with sparse coding. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 2067\u20132073 (2017)","DOI":"10.24963\/ijcai.2017\/287"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Li, Z., Xu, M., Nie, J., Kang, J., Chen, W., Xie, S.: Noma-enabled cooperative computation offloading for blockchain-empowered internet of things: a learning approach. IEEE Internet Things J. 8, 2364\u20132378(2020)","DOI":"10.1109\/JIOT.2020.3016644"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Liu, V., Kumaraswamy, R., Le, L., White, M.: The utility of sparse representations for control in reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4384\u20134391 (2019)","DOI":"10.1609\/aaai.v33i01.33014384"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Luo, X., Meng, Q., Di He, W.C., Wang, Y.: I4r: promoting deep reinforcement learning by the indicator for expressive representations. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence, pp. 2669\u20132675 (2020)","DOI":"10.24963\/ijcai.2020\/370"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Sarafian, E., Tamar, A., Kraus, S.: Constrained policy improvement for efficient reinforcement learning. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence (2020)","DOI":"10.24963\/ijcai.2020\/396"},{"issue":"1","key":"7_CR11","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR12","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"7_CR13","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"7_CR14","unstructured":"Van Hasselt, H., Doron, Y., Strub, F., Hessel, M., Sonnerat, N., Modayil, J.: Deep reinforcement learning and the deadly triad. arXiv preprint arXiv:1812.02648 (2018)"},{"key":"7_CR15","unstructured":"Wang, K., Kang, B., Shao, J., Feng, J.: Improving generalization in reinforcement learning with mixture regularization. In: Conference on Neural Information Processing Systems (2020)"},{"key":"7_CR16","unstructured":"Wang, K., Kang, B., Shao, J., Feng, J.: Improving generalization in reinforcement learning with mixture regularization. In: Advances in Neural Information Processing Systems (2020)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","DOI":"10.1007\/BF00992698"},{"issue":"7","key":"7_CR18","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1109\/TNNLS.2012.2197412","volume":"23","author":"Z Xu","year":"2012","unstructured":"Xu, Z., Chang, X., Xu, F., Zhang, H.: $$l_ {1\/2}$$ regularization: a thresholding representation theory and a fast solver. IEEE Trans. Neural Networks Learn. Syst. 23(7), 1013\u20131027 (2012)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Zhao, H., Wu, J., Li, Z., Chen, W., Zheng, Z.: Double sparse deep reinforcement learning via multilayer sparse coding and nonconvex regularized pruning. IEEE Transactions on Cybernetics (2022)","DOI":"10.1109\/TCYB.2022.3157892"},{"key":"7_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108364","volume":"242","author":"H Zhao","year":"2022","unstructured":"Zhao, H., Zhong, P., Chen, H., Li, Z., Chen, W., Zheng, Z.: Group non-convex sparsity regularized partially shared dictionary learning for multi-view learning. Knowl. Based Syst. 242, 108364 (2022)","journal-title":"Knowl. Based Syst."},{"key":"7_CR21","unstructured":"Zhou, Q., Kuang, Y., Qiu, Z., Li, H., Wang, J.: Promoting stochasticity for expressive policies via a simple and efficient regularization method. Adv. Neural Inform. Process. Syst. 33 (2020)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20503-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:29:36Z","timestamp":1671193776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20503-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031205026","9783031205033"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20503-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}