{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:54:45Z","timestamp":1775638485421,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11704-021-0354-4","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:02:46Z","timestamp":1641600166000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient policy evaluation by matrix sketching"],"prefix":"10.1007","volume":"16","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,8]]},"reference":[{"key":"354_CR1","volume-title":"Reinforcement Learning: an Introduction","author":"R S Sutton","year":"2018","unstructured":"Sutton R S, Barto A G. Reinforcement Learning: an Introduction. 2nd ed. London: MIT Press, 2018","edition":"2nd ed."},{"key":"354_CR2","doi-asserted-by":"crossref","unstructured":"Bertsekas D P, Tsitsiklis J N. Neuro-dynamic programming: an overview. In: Proceedings of the 34th IEEE Conference on Decision and Control. 1995, 560\u2013564","DOI":"10.1109\/CDC.1995.478953"},{"key":"354_CR3","first-page":"1107","volume":"4","author":"M G Lagoudakis","year":"2003","unstructured":"Lagoudakis M G, Parr R. Least-squares policy iteration. Journal of Machine Learning Research, 2003, 4: 1107\u20131149","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"354_CR4","first-page":"809","volume":"15","author":"C Dann","year":"2014","unstructured":"Dann C, Neumann G, Peters J. Policy evaluation with temporal differences: a survey and comparison. The Journal of Machine Learning Research, 2014, 15(1): 809\u2013883","journal-title":"The Journal of Machine Learning Research"},{"issue":"1","key":"354_CR5","first-page":"289","volume":"15","author":"M Geist","year":"2014","unstructured":"Geist M, Scherrer B. Off-policy learning with eligibility traces: a survey. The Journal of Machine Learning Research, 2014, 15(1): 289\u2013333","journal-title":"The Journal of Machine Learning Research"},{"key":"354_CR6","unstructured":"Liang Y T, Machado M C, Talvitie E, Bowling M. State of the art control of Atari games using shallow reinforcement learning. In: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems. 2016, 485\u2013493"},{"key":"354_CR7","unstructured":"Tagorti M, Scherrer B. On the rate of convergence and error bounds for LSTD (\u03bb). In: Proceedings of the 32nd International Conference on International Conference on Machine Learning. 2015, 1521\u20131529"},{"issue":"1","key":"354_CR8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF00115009","volume":"3","author":"R S Sutton","year":"1988","unstructured":"Sutton R S. Learning to predict by the methods of temporal differences. Machine Learning, 1988, 3(1): 9\u201344","journal-title":"Machine Learning"},{"key":"354_CR9","unstructured":"Sutton R S, Szepesv\u00e1ri C, Maei H R. A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation. In: Proceedings of the 21st International Conference on Neural Information Processing Systems. 2008, 1609\u20131616"},{"issue":"2\u20133","key":"354_CR10","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/A:1017936530646","volume":"49","author":"J A Boyan","year":"2002","unstructured":"Boyan J A. Technical update: least-squares temporal difference learning. Machine Learning, 2002, 49(2\u20133): 233\u2013246","journal-title":"Machine Learning"},{"key":"354_CR11","unstructured":"Geramifard A, Bowling M H, Sutton R S. Incremental least-squares temporal difference learning. In: Proceedings of the 21st National Conference on Artificial Intelligence and the Eighteenth Innovative Applications of Artificial Intelligence Conference. 2006, 356\u2013361"},{"key":"354_CR12","doi-asserted-by":"crossref","unstructured":"Geramifard A, Bowling M H, Zinkevich M, Sutton R S. iLSTD: eligibility traces and convergence analysis. In: Proceedings of the 20th Annual Conference on Neural Information Processing Systems. 2006, 441\u2013448","DOI":"10.7551\/mitpress\/7503.003.0060"},{"key":"354_CR13","doi-asserted-by":"crossref","unstructured":"Pan Y C, White A M, White M. Accelerated gradient temporal difference learning. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017, 2464\u20132470","DOI":"10.1609\/aaai.v31i1.10829"},{"key":"354_CR14","unstructured":"Ghavamzadeh M, Lazaric A, Maillard O A, Munos R. LSTD with random projections. In: Proceedings of Advances in Neural Information Processing Systems: 24th Annual Conference on Neural Information Processing Systems 2010. 2010, 721\u2013729"},{"key":"354_CR15","unstructured":"Pan Y C, Azer E S, White M. Effective sketching methods for value function approximation. In: Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence. 2017"},{"key":"354_CR16","unstructured":"Gehring C, Pan Y C, White M. Incremental truncated LSTD. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2016, 1505\u20131511"},{"key":"354_CR17","doi-asserted-by":"crossref","unstructured":"Li H F, Xia Y C, Zhang W S. Finite sample analysis of LSTD with random projections and eligibility traces. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018, 2390\u20132396","DOI":"10.24963\/ijcai.2018\/331"},{"issue":"1\u20132","key":"354_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0400000060","volume":"10","author":"D P Woodruff","year":"2014","unstructured":"Woodruff D P. Sketching as a tool for numerical linear algebra. Foundations and Trends\u00ae in Theoretical Computer Science, 2014, 10(1\u20132): 1\u2013157","journal-title":"Foundations and Trends\u00ae in Theoretical Computer Science"},{"key":"354_CR19","volume-title":"Dynamic Programming and Optimal Control","author":"D P Bertsekas","year":"1995","unstructured":"Bertsekas D P. Dynamic Programming and Optimal Control. Volume 1. Belmont: Athena Scientific, 1995"},{"key":"354_CR20","doi-asserted-by":"crossref","unstructured":"Kolter J Z, Ng A Y. Regularization and feature selection in least-squares temporal difference learning. In: Proceedings of the 26th Annual International Conference on Machine Learning. 2009, 521\u2013528","DOI":"10.1145\/1553374.1553442"},{"issue":"1\u20133","key":"354_CR21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/BF00114723","volume":"22","author":"S J Bradtke","year":"1996","unstructured":"Bradtke S J, Barto A G. Linear least-squares algorithms for temporal difference learning. Machine Learning, 1996, 22(1\u20133): 33\u201357","journal-title":"Machine Learning"},{"key":"354_CR22","doi-asserted-by":"crossref","unstructured":"Liberty E. Simple and deterministic matrix sketching. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2013, 581\u2013588","DOI":"10.1145\/2487575.2487623"},{"issue":"5","key":"354_CR23","doi-asserted-by":"publisher","first-page":"1762","DOI":"10.1137\/15M1009718","volume":"45","author":"M Ghashami","year":"2016","unstructured":"Ghashami M, Liberty E, Phillips J M, Woodruff D P. Frequent directions: simple and deterministic matrix sketching. SIAM Journal on Computing, 2016, 45(5): 1762\u20131792","journal-title":"SIAM Journal on Computing"},{"key":"354_CR24","unstructured":"Kuzborskij I, Cella L, Cesa-Bianchi N. Efficient linear bandits through matrix sketching. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics. 2019, 177\u2013185"},{"key":"354_CR25","unstructured":"Luo H P, Agarwal A, Cesa-Bianchi N, Langford J. Efficient second order online learning by sketching. In: Proceedings of Advances in Neural Information Processing Systems. 2016, 902\u2013910"},{"issue":"45","key":"354_CR26","first-page":"1","volume":"20","author":"L Luo","year":"2019","unstructured":"Luo L, Chen C, Zhang Z H, Li W J, Zhang T. Robust frequent directions with application in online learning. Journal of Machine Learning Research, 2019, 20(45): 1\u201341","journal-title":"Journal of Machine Learning Research"},{"key":"354_CR27","unstructured":"Mroueh Y, Marcheret E, Goel V. Co-occurring directions sketching for approximate matrix multiply. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. 2017, 567\u2013575"},{"key":"354_CR28","doi-asserted-by":"crossref","unstructured":"Brand M. Fast online SVD revisions for lightweight recommender systems. In: Proceedings of the 2003 SIAM International Conference on Data Mining. 2003, 37\u201346","DOI":"10.1137\/1.9781611972733.4"},{"key":"354_CR29","unstructured":"Sarwar B, Karypis G, Konstan J, Riedl J. Incremental singular value decomposition algorithms for highly scalable recommender systems. In: Proceedings of the 5th International Conference on Computer and Information Science. 2002, 27\u201328"},{"issue":"1\u20133","key":"354_CR30","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s11263-007-0075-7","volume":"77","author":"D A Ross","year":"2008","unstructured":"Ross D A, Lim J, Lin R S, Yang M H. Incremental learning for robust visual tracking. International Journal of Computer Vision, 2008, 77(1\u20133): 125\u2013141","journal-title":"International Journal of Computer Vision"},{"key":"354_CR31","doi-asserted-by":"crossref","unstructured":"Hall P M, Marshall D, Martin R R. Incremental eigenanalysis for classification. In: Proceedings of the British Machine Vision Conference. 1998, 1\u201310","DOI":"10.5244\/C.12.29"},{"key":"354_CR32","doi-asserted-by":"crossref","unstructured":"Brand M. Incremental singular value decomposition of uncertain data with missing values. In: Proceedings of the 7th European Conference on Computer Vision. 2002, 707\u2013720","DOI":"10.1007\/3-540-47969-4_47"},{"issue":"1","key":"354_CR33","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.laa.2005.07.021","volume":"415","author":"M Brand","year":"2006","unstructured":"Brand M. Fast low-rank modifications of the thin singular value decomposition. Linear Algebra and its Applications, 2006, 415(1): 20\u201330","journal-title":"Linear Algebra and its Applications"},{"issue":"1","key":"354_CR34","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1287\/ijoc.2017.0768","volume":"30","author":"D F Salas","year":"2018","unstructured":"Salas D F, Powell W B. Benchmarking a scalable approximate dynamic programming algorithm for stochastic control of grid-level energy storage. INFORMS Journal on Computing, 2018, 30(1): 106\u2013123","journal-title":"INFORMS Journal on Computing"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-021-0354-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-021-0354-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-021-0354-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T22:09:49Z","timestamp":1726438189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-021-0354-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["354"],"URL":"https:\/\/doi.org\/10.1007\/s11704-021-0354-4","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,8]]},"assertion":[{"value":"17 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"165330"}}