{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:17:49Z","timestamp":1762543069671,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T00:00:00Z","timestamp":1562198400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T00:00:00Z","timestamp":1562198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evolving Systems"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s12530-019-09290-9","type":"journal-article","created":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T16:03:45Z","timestamp":1562256225000},"page":"89-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Clustering subspace generalization to obtain faster reinforcement learning"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6357-3311","authenticated-orcid":false,"given":"Maryam","family":"Hashemzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3669-760X","authenticated-orcid":false,"given":"Reshad","family":"Hosseini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6370-6057","authenticated-orcid":false,"given":"Majid Nili","family":"Ahmadabadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,4]]},"reference":[{"key":"9290_CR1","first-page":"550","volume-title":"Advances in neural information processing systems 2","author":"DH Ackley","year":"1990","unstructured":"Ackley DH, Littman ML (1990) Generalization and scaling in reinforcement learning. In: Advances in neural information processing systems 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp 550\u2013557"},{"issue":"2","key":"9290_CR2","first-page":"29","volume":"8","author":"P Angelov","year":"2014","unstructured":"Angelov P (2014) Outside the box: an alternative data analytics framework. J Autom Mobile Robot Intell Syst 8(2):29\u201335","journal-title":"J Autom Mobile Robot Intell Syst"},{"key":"9290_CR3","first-page":"76","volume-title":"IEEE International Conference on Fuzzy Systems","author":"P Angelov","year":"2005","unstructured":"Angelov P, Kasabov N (2005) Evolving computational intelligence systems. In: IEEE International Conference on Fuzzy Systems. IEEE, Brisbane, QLD, Australia, pp 76\u201382"},{"doi-asserted-by":"crossref","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA (2017) A brief survey of deep reinforcement learning. \narXiv:1708.05866","key":"9290_CR4","DOI":"10.1109\/MSP.2017.2743240"},{"key":"9290_CR5","first-page":"89","volume":"21","author":"P Auer","year":"2009","unstructured":"Auer P, Jaksch T, Ortner R (2009) Near-optimal regret bounds for reinforcement learning. Adv Neural Inf Process Syst 21:89\u201396","journal-title":"Adv Neural Inf Process Syst"},{"key":"9290_CR500","first-page":"1","volume-title":"IEEE International Conference on Fuzzy Systems","author":"RD Baruah","year":"2012","unstructured":"Baruah RD, Angelov P (2012) Evolving local means method for clustering of streaming data. In:  IEEE International Conference on Fuzzy Systems. IEEE, Brisbane, QLD, Australia, pp 1\u20138"},{"issue":"9","key":"9290_CR6","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1109\/TCYB.2013.2291234","volume":"44","author":"RD Baruah","year":"2013","unstructured":"Baruah RD, Angelov P (2013) Dec: Dynamically evolving clustering and its application to structure identification of evolving fuzzy models. IEEE Trans Cybern 44(9):1619\u20131631","journal-title":"IEEE Trans Cybern"},{"unstructured":"Bruce J, S\u00fcnderhauf N, Mirowski P, Hadsell R, Milford M (2017) One-shot reinforcement learning for robot navigation with interactive replay. \narXiv:1711.10137","key":"9290_CR7"},{"issue":"12","key":"9290_CR8","doi-asserted-by":"publisher","first-page":"e115926","DOI":"10.1371\/journal.pone.0115926","volume":"9","author":"P Daee","year":"2014","unstructured":"Daee P, Mirian MS, Ahmadabadi MN (2014) Reward maximization justifies the transition from sensory selection at childhood to sensory integration at adulthood. PLoS One 9(12):e115926","journal-title":"PLoS One"},{"doi-asserted-by":"crossref","unstructured":"Gu S, Holly E, Lillicrap T, Levine S (2017) Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 3389\u20133396","key":"9290_CR9","DOI":"10.1109\/ICRA.2017.7989385"},{"unstructured":"Gupta A, Devin C, Liu Y, Abbeel P, Levine S (2017) Learning invariant feature spaces to transfer skills with reinforcement learning. \narXiv:1703.02949","key":"9290_CR10"},{"key":"9290_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869978","author":"M Hashemzadeh","year":"2018","unstructured":"Hashemzadeh M, Hosseini R, Ahmadabadi MN (2018) Exploiting generalization in the subspaces for faster model-based reinforcement learning. IEEE Trans Neural Netw Learn Syst. \nhttps:\/\/doi.org\/10.1109\/TNNLS.2018.2869978","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"unstructured":"Hausknecht M, Stone P (2015) Deep recurrent Q-learning for partially observable MDPs. \narXiv:1507.06527","key":"9290_CR12"},{"doi-asserted-by":"crossref","unstructured":"Hemminghaus J, Kopp S (2017) Towards adaptive social behavior generation for assistive robots using reinforcement learning. In: Proceedings of the 2017 ACM\/IEEE International Conference on Human-Robot Interaction. ACM, New York, pp 332\u2013340","key":"9290_CR13","DOI":"10.1145\/2909824.3020217"},{"issue":"301","key":"9290_CR14","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","volume":"58","author":"W Hoeffding","year":"1963","unstructured":"Hoeffding W (1963) Probability inequalities for sums of bounded random variables. J Am Stat Assoc 58(301):13\u201330","journal-title":"J Am Stat Assoc"},{"key":"9290_CR15","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.ins.2016.12.004","volume":"382","author":"R Hyde","year":"2017","unstructured":"Hyde R, Angelov P, MacKenzie AR (2017) Fully online clustering of evolving data streams into arbitrarily shaped clusters. Inf Sci 382:96\u2013114","journal-title":"Inf Sci"},{"key":"9290_CR16","first-page":"2619","volume":"3","author":"N Kohl","year":"2004","unstructured":"Kohl N, Stone P (2004) Policy gradient reinforcement learning for fast quadrupedal locomotion. IEEE Int Conf Robot Autom (ICRA) 3:2619\u20132624","journal-title":"IEEE Int Conf Robot Autom (ICRA)"},{"key":"9290_CR17","first-page":"3675","volume-title":"Advances in neural information processing systems","author":"TD Kulkarni","year":"2016","unstructured":"Kulkarni TD, Narasimhan K, Saeedi A, Tenenbaum J (2016) Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: Advances in neural information processing systems, vol 29. Curran Associates, Inc., New York, pp 3675\u20133683"},{"unstructured":"Lai M (2015) Giraffe: using deep reinforcement learning to play chess. \narXiv:1509.01549","key":"9290_CR18"},{"issue":"1","key":"9290_CR19","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TMECH.2017.2717461","volume":"23","author":"Z Li","year":"2018","unstructured":"Li Z, Zhao T, Chen F, Yingbai H, Chun-Yi S, Fukuda T (2018) Reinforcement learning of manipulation and grasping using dynamical movement primitives for a humanoidlike mobile manipulator. IEEE\/ASME Trans Mech 23(1):121\u2013131","journal-title":"IEEE\/ASME Trans Mech"},{"key":"9290_CR20","first-page":"183","volume-title":"Proceedings of the Tenth National Conference on Artificial Intelligence","author":"C Lonnie","year":"1992","unstructured":"Lonnie C (1992) Reinforcement learning with perceptual aliasing: The perceptual distinctions approach. In: Proceedings of the Tenth National Conference on Artificial Intelligence. AAAI Press,  San Jose, California, pp 183\u2013188"},{"issue":"2","key":"9290_CR21","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1111\/j.1558-5646.1957.tb02884.x","volume":"11","author":"CD Michener","year":"1957","unstructured":"Michener CD, Sokal RR (1957) A quantitative approach to a problem in classification. Evolution 11(2):130\u2013162","journal-title":"Evolution"},{"issue":"7540","key":"9290_CR22","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, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529","journal-title":"Nature"},{"unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp 1928\u20131937","key":"9290_CR23"},{"key":"9290_CR24","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-319-40533-9_8","volume-title":"Trends in control and decision-making for human\u2013robot collaboration systems","author":"H Modares","year":"2017","unstructured":"Modares H , Ranatunga I, AlQaudi B, Lewis FL, Popa DO (2017) Intelligent human\u2013robot interaction systems using reinforcement learning and neural networks. In: Trends in control and decision-making for human\u2013robot collaboration systems.  Springer,  Switzerland, pp 153\u2013176"},{"key":"9290_CR25","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/11552246_35","volume-title":"Experimental robotics IX","author":"AY Ng","year":"2006","unstructured":"Ng AY, Coates A, Diel M, Ganapathi V, Schulte J, Tse B, Berger E, Liang E (2006) Autonomous inverted helicopter flight via reinforcement learning. In: Experimental robotics IX. Springer, Berlin, pp 363\u2013372"},{"key":"9290_CR26","first-page":"2863","volume-title":"Advances in neural information processing systems","author":"J Oh","year":"2015","unstructured":"Oh J, Guo X, Lee H, Lewis RL, Singh S (2015) Action-conditional video prediction using deep networks in atari games. In: Advances in neural information processing systems, vol 28. Curran Associates, Inc., New York, pp 2863\u20132871"},{"unstructured":"Popov I, Heess N, Lillicrap T, Hafner R, Barth-Maron G, Vecerik M, Lampe T, Tassa Y, Erez T, Riedmiller M (2017) Data-efficient deep reinforcement learning for dexterous manipulation. \narXiv:1704.03073","key":"9290_CR27"},{"key":"9290_CR28","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"ML Puterman","year":"1994","unstructured":"Puterman ML (1994) Markov decision processes: discrete stochastic dynamic programming. Wiley, New York"},{"unstructured":"Rajeswaran A, Kumar V, Gupta A, Schulman J, Todorov E, Levine S (2017) Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. \narXiv:1709.10087","key":"9290_CR29"},{"key":"9290_CR30","volume-title":"Reinforcement learning: an introduction","author":"SS Richard","year":"2018","unstructured":"Richard SS, Andrew GB (2018) Reinforcement learning: an introduction. MIT press, Cambridge"},{"key":"9290_CR31","first-page":"1889","volume-title":"International Conference on Machine Learning","author":"J Schulman","year":"2015","unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International Conference on Machine Learning. PMLR, France, pp 1889\u20131897"},{"key":"9290_CR32","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.patrec.2016.08.009","volume":"87","author":"F Shoeleh","year":"2017","unstructured":"Shoeleh F, Asadpour M (2017) Graph based skill acquisition and transfer learning for continuous reinforcement learning domains. Pattern Recogn Lett 87:104\u2013116","journal-title":"Pattern Recogn Lett"},{"issue":"7587","key":"9290_CR33","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den\u00a0Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"key":"9290_CR34","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1613\/jair.859","volume":"16","author":"S Singh","year":"2002","unstructured":"Singh S, Litman D, Kearns M, Walker M (2002) Optimizing dialogue management with reinforcement learning: experiments with the NJFun system. J Artif Intell Res 16:105\u2013133","journal-title":"J Artif Intell Res"},{"unstructured":"Stadie BC, Levine S, Abbeel P (2015) Incentivizing exploration in reinforcement learning with deep predictive models. \narXiv:1507.00814","key":"9290_CR35"},{"issue":"3","key":"9290_CR36","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone P, Veloso M (2000) Multiagent systems: a survey from a machine learning perspective. Auton Robots 8(3):345\u2013383","journal-title":"Auton Robots"},{"key":"9290_CR37","first-page":"1038","volume-title":"Advances in neural information processing systems 8","author":"RS Sutton","year":"1995","unstructured":"Sutton RS (1995) Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Advances in neural information processing systems 8.  MIT Press, Cambridge, MA, pp 1038\u20131044"},{"unstructured":"Synnaeve G, Nardelli N, Auvolat A, Chintala S, Lacroix T, Lin Z, Richoux F, Usunier N (2016) Torchcraft: a library for machine learning research on real-time strategy games. \narXiv:1611.00625","key":"9290_CR38"},{"issue":"3","key":"9290_CR39","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro G (1995) Temporal difference learning and TD-Gammon. Commun ACM 38(3):58\u201368","journal-title":"Commun ACM"},{"key":"9290_CR40","first-page":"361","volume-title":"Proceedings of the international conference on machine learning","author":"H Van Seijen","year":"2013","unstructured":"Van\u00a0Seijen H, Sutton RS (2013) Efficient planning in mdps by small backups. In: Proceedings of the international conference on machine learning. JMLR, Atlanta, GA, USA, pp 361\u2013369"},{"unstructured":"Vinyals O, Ewalds T, Bartunov S, Georgiev P, Vezhnevets AS, Yeo M, Makhzani A, K\u00fcttler H, Agapiou J, Schrittwieser J et\u00a0al (2017) Starcraft II: a new challenge for reinforcement learning. \narXiv:1708.04782","key":"9290_CR41"},{"unstructured":"Wang W, Hao J, Wang Y, Taylor M (2018) Towards cooperation in sequential prisoner\u2019s dilemmas: a deep multiagent reinforcement learning approach. \narXiv:1803.00162","key":"9290_CR42"},{"unstructured":"Weissman Tsachy, Ordentlich Erik, Seroussi Gadiel, Verdu Sergio, Weinberger Marcelo\u00a0J (2003) Inequalities for the $$\\text{L}_1$$ deviation of the empirical distribution. Technical report, HP Laboratories Palo Alto","key":"9290_CR43"},{"doi-asserted-by":"crossref","unstructured":"Zhu Y, Mottaghi R, Kolve E, Lim JJ, Gupta A, Fei-Fei L, Farhadi A (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 3357\u20133364","key":"9290_CR44","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["Evolving Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-019-09290-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12530-019-09290-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-019-09290-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T23:18:43Z","timestamp":1593731923000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12530-019-09290-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,4]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["9290"],"URL":"https:\/\/doi.org\/10.1007\/s12530-019-09290-9","relation":{},"ISSN":["1868-6478","1868-6486"],"issn-type":[{"type":"print","value":"1868-6478"},{"type":"electronic","value":"1868-6486"}],"subject":[],"published":{"date-parts":[[2019,7,4]]},"assertion":[{"value":"2 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}