{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T08:49:20Z","timestamp":1760345360528,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003968","name":"Iran National Science Foundation","doi-asserted-by":"crossref","award":["98002017","98002017","98002017"],"award-info":[{"award-number":["98002017","98002017","98002017"]}],"id":[{"id":"10.13039\/501100003968","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s11227-023-05854-4","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T20:02:32Z","timestamp":1704312152000},"page":"10720-10745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Local and soft feature selection for value function approximation in batch reinforcement learning for robot navigation"],"prefix":"10.1007","volume":"80","author":[{"given":"Fatemeh","family":"Fathinezhad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peyman","family":"Adibi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bijan","family":"Shoushtarian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jocelyn","family":"Chanussot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,3]]},"reference":[{"key":"5854_CR1","first-page":"13","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT press, NJ, p 13"},{"key":"5854_CR2","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.patrec.2017.06.004","volume":"107","author":"W Liu","year":"2018","unstructured":"Liu W, Zhang L, Tao D, Cheng J (2018) Reinforcement online learning for emotion prediction by using physiological signals. Patt Recogn Lett 107:123\u2013130","journal-title":"Patt Recogn Lett"},{"key":"5854_CR3","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.eswa.2019.01.023","volume":"122","author":"J Parras","year":"2019","unstructured":"Parras J, Zazo S (2019) Learning attack mechanisms in wireless sensor networks using markov decision processes. Expert Syst Appl 122:376\u2013387","journal-title":"Expert Syst Appl"},{"key":"5854_CR4","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.engappai.2019.04.001","volume":"83","author":"SR Friedrich","year":"2019","unstructured":"Friedrich SR, Schreibauer M, Buss M (2019) Least-squares policy iteration algorithms for robotics: online, continuous, and automatic. Eng Appl Artif Intell 83:72\u201384","journal-title":"Eng Appl Artif Intell"},{"key":"5854_CR5","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J Baxter","year":"2001","unstructured":"Baxter J, Bartlett PL (2001) Infinite-horizon policy-gradient estimation. J Artif Intell Res 15:319\u2013350","journal-title":"J Artif Intell Res"},{"issue":"6","key":"5854_CR6","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TNNLS.2013.2247418","volume":"24","author":"M Geist","year":"2013","unstructured":"Geist M, Pietquin O (2013) Algorithmic survey of parametric value function approximation. IEEE Trans Neural Netw Learn Syst 24(6):845\u2013867","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"5854_CR7","unstructured":"Konda VR, Tsitsiklis JN (2000) Actor-critic algorithms, pp 1008\u20131014"},{"key":"5854_CR8","first-page":"1038","volume":"8","author":"RS Sutton","year":"1996","unstructured":"Sutton RS (1996) Generalization in reinforcement learning: successful examples using sparse coarse coding. Adv Neural Inform Process Syst. 8:1038\u20131044","journal-title":"Adv Neural Inform Process Syst."},{"key":"5854_CR9","first-page":"1107","volume":"4","author":"MG Lagoudaki","year":"2003","unstructured":"Lagoudaki MG, Parr R (2003) Least-squares policy iteration. J Mach Learn Res 4:1107\u20131149","journal-title":"J Mach Learn Res"},{"key":"5854_CR10","doi-asserted-by":"crossref","unstructured":"Parr R, Li L, Taylor G, Painter-Wakefield C, Littman ML (2008) An Analysis of Linear Models, Linear value-function approximation, and feature selection for reinforcement learning, pp 752\u2013759","DOI":"10.1145\/1390156.1390251"},{"key":"5854_CR11","doi-asserted-by":"crossref","unstructured":"Zhang G, Iwata T, Kashima H (2018) On reducing dimensionality of labeled data efficiently, pp 77\u201388. Springer","DOI":"10.1007\/978-3-319-93040-4_7"},{"key":"5854_CR12","doi-asserted-by":"crossref","unstructured":"Kroon M, Whiteson S (2008) Automatic feature selection for model-based reinforcement learning in factored mdps, 324\u2013330. IEEE","DOI":"10.1109\/ICMLA.2009.71"},{"issue":"2","key":"5854_CR13","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1109\/TMECH.2021.3072675","volume":"27","author":"Y Zhu","year":"2021","unstructured":"Zhu Y, Wang Z, Chen C, Dong D (2021) Rule-based reinforcement learning for efficient robot navigation with space reduction. IEEE\/ASME Trans Mech 27(2):846\u2013857","journal-title":"IEEE\/ASME Trans Mech"},{"issue":"4","key":"5854_CR14","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1017\/S0263574720000570","volume":"39","author":"LA Moreira","year":"2021","unstructured":"Moreira LA, Justel CM, de Oliveira JC, Rosa PF (2021) Development of a method for data dimensionality reduction in loop closure detection: an incremental approach. Robotica 39(4):557\u2013571","journal-title":"Robotica"},{"key":"5854_CR15","doi-asserted-by":"crossref","unstructured":"Morimoto J, Hyon S-H, Atkeson CG, Cheng G (2016) Low-dimensional feature extraction for humanoid locomotion using kernel dimension reduction, pp 2711\u20132716 IEEE","DOI":"10.1109\/ROBOT.2008.4543621"},{"key":"5854_CR16","doi-asserted-by":"publisher","first-page":"42619","DOI":"10.1109\/ACCESS.2020.2977379","volume":"8","author":"H Yu","year":"2020","unstructured":"Yu H, Lu W, Han Y, Liu D, Zhang M (2020) Heterogeneous dimensionality reduction for efficient motion planning in high-dimensional spaces. IEEE Access 8:42619\u201342632","journal-title":"IEEE Access"},{"key":"5854_CR17","doi-asserted-by":"crossref","unstructured":"Khalilullah KI, Jindai M, Ota S, Yasuda T (2018) Fast road detection methods on a large scale dataset for assisting robot navigation using kernel principal component analysis and deep learning, pp 798\u2013803, IEEE","DOI":"10.23919\/SICE.2018.8492578"},{"issue":"1","key":"5854_CR18","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s12530-019-09290-9","volume":"11","author":"M Hashemzadeh","year":"2020","unstructured":"Hashemzadeh M, Hosseini R, Ahmadabadi MN (2020) Clustering subspace generalization to obtain faster reinforcement learning. Evolv Syst 11(1):89\u2013103","journal-title":"Evolv Syst"},{"key":"5854_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2016.08.005","volume":"84","author":"V Tangkaratt","year":"2016","unstructured":"Tangkaratt V, Morimoto J, Sugiyama M (2016) Model-based reinforcement learning with dimension reduction. Neural Netw 84:1\u201316","journal-title":"Neural Netw"},{"issue":"1","key":"5854_CR20","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1162\/NECO_a_00683","volume":"27","author":"V Tangkaratt","year":"2015","unstructured":"Tangkaratt V, Xie N, Sugiyama M (2015) Conditional density estimation with dimensionality reduction via squared-loss conditional entropy minimization. Neural Computat 27(1):228\u2013254","journal-title":"Neural Computat"},{"issue":"4","key":"5854_CR21","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X Xu","year":"2007","unstructured":"Xu X, Hu D, Lu X (2007) Kernel-based least squares policy iteration for reinforcement learning. IEEE Trans Neural Netw 18(4):973\u2013992","journal-title":"IEEE Trans Neural Netw"},{"key":"5854_CR22","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.neunet.2017.06.007","volume":"94","author":"Y Cui","year":"2017","unstructured":"Cui Y, Matsubara T, Sugimoto K (2017) Kernel dynamic policy programming: Applicable reinforcement learning to robot systems with high dimensional states. Neural Netw 94:13\u201323","journal-title":"Neural Netw"},{"key":"5854_CR23","unstructured":"Boyan JA (1999) Least-squares temporal difference learning, pp 49\u201356"},{"issue":"1","key":"5854_CR24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3233\/ICA-180578","volume":"26","author":"A Prieto","year":"2019","unstructured":"Prieto A, Romero A, Bellas F, Salgado R, Duro RJ (2019) Introducing separable utility regions in a motivational engine for cognitive developmental robotics. Integr Comput Aid Eng 26(1):3\u201320","journal-title":"Integr Comput Aid Eng"},{"key":"5854_CR25","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.neucom.2018.07.093","volume":"353","author":"A Romero","year":"2019","unstructured":"Romero A, Prieto A, Bellas F, Duro RJ (2019) Simplifying the creation and management of utility models in continuous domains for cognitive robotics. Neurocomputing 353:106\u2013118","journal-title":"Neurocomputing"},{"issue":"2","key":"5854_CR26","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1016\/0022-247X(85)90317-8","volume":"110","author":"PJ Schweitzer","year":"1985","unstructured":"Schweitzer PJ, Seidmann A (1985) Generalized polynomial approximations in markovian decision processes. J Math Anal Appl 110(2):568\u2013582","journal-title":"J Math Anal Appl"},{"key":"5854_CR27","unstructured":"Cover TM, Thomas JA (2006) Elements of information theory 2nd edition (wiley series in telecommunications and signal processing)"},{"issue":"2","key":"5854_CR28","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TNN.2008.2005601","volume":"20","author":"PA Est\u00e9vez","year":"2009","unstructured":"Est\u00e9vez PA, Tesmer M, Perez CA, Zurada JM (2009) Normalized mutual information feature selection. IEEE Trans Neural Netw 20(2):189\u2013201","journal-title":"IEEE Trans Neural Netw"},{"issue":"3","key":"5854_CR29","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1016\/j.ejor.2010.02.032","volume":"206","author":"A Unler","year":"2010","unstructured":"Unler A, Murat A (2010) A discrete particle swarm optimization method for feature selection in binary classification problems. Europ J Operat Res 206(3):528\u2013539","journal-title":"Europ J Operat Res"},{"issue":"3","key":"5854_CR30","doi-asserted-by":"crossref","first-page":"172988141771079","DOI":"10.1177\/1729881417710794","volume":"14","author":"D Nemec","year":"2017","unstructured":"Nemec D, Janota A, Hrubo\u0161 M, Gregor M, Pirn\u00edk R (2017) Mutual acoustic identification in the swarm of e-puck robots. Int J Adv Rob Syst 14(3):1729881417710794","journal-title":"Int J Adv Rob Syst"},{"issue":"4","key":"5854_CR31","doi-asserted-by":"publisher","first-page":"111","DOI":"10.3233\/IFS-2012-0500","volume":"23","author":"MS Mirian","year":"2012","unstructured":"Mirian MS, Araabi BN, Ahmadabadi MN, Siegwart RR (2012) Metal: a framework for mixture-of-experts task and attention learning. J Intell Fuzzy Syst 23(4):111\u2013128","journal-title":"J Intell Fuzzy Syst"},{"key":"5854_CR32","first-page":"2169","volume":"8","author":"S Mahadevan","year":"2007","unstructured":"Mahadevan S, Maggioni M (2007) Proto-value functions: a laplacian framework for learning representation and control in markov decision processes. J Mach Learn Res 8:2169\u20132231","journal-title":"J Mach Learn Res"},{"key":"5854_CR33","first-page":"560","volume":"1","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas DP, Tsitsiklis JN (1995) Neuro-dynamic programming: an overview. Proc Conf Decis Control 1:560\u2013564","journal-title":"Proc Conf Decis Control"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05854-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05854-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05854-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T10:40:48Z","timestamp":1730976048000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05854-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":33,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["5854"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05854-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2024,1,3]]},"assertion":[{"value":"2 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}