{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T13:35:34Z","timestamp":1692797734618},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2014,7,10]],"date-time":"2014-07-10T00:00:00Z","timestamp":1404950400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1007\/s10458-014-9268-y","type":"journal-article","created":{"date-parts":[[2014,7,9]],"date-time":"2014-07-09T11:32:31Z","timestamp":1404905551000},"page":"754-786","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Predictive feature selection for genetic policy search"],"prefix":"10.1007","volume":"29","author":[{"given":"Steven","family":"Loscalzo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Wright","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,10]]},"reference":[{"key":"9268_CR1","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009). A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57, 469\u2013483.","journal-title":"Robotics and Autonomous Systems"},{"key":"9268_CR2","volume-title":"Dynamic programming","author":"R Bellman","year":"2003","unstructured":"Bellman, R. (2003). Dynamic programming. Mineola: Dover Publications."},{"key":"9268_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. In Proceedings of the 26th annual international conference on machine learning (pp. 41\u201348). New York: ACM.","DOI":"10.1145\/1553374.1553380"},{"key":"9268_CR4","first-page":"118","volume-title":"Lernen, Wissensentdeckung und Adaptivit\u00e4t (LWA)","author":"N B\u00f6hm","year":"2004","unstructured":"B\u00f6hm, N., Kkai, G., & Mandl, S. (2004). Evolving a heuristic function for the game of tetris. Lernen, Wissensentdeckung und Adaptivit\u00e4t (LWA) (pp. 118\u2013122). Berlin: Humbold-Universit\u00e4t."},{"key":"9268_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.575","volume":"11","author":"C Boutilier","year":"1999","unstructured":"Boutilier, C., Dean, T., & Hanks, S. (1999). Decision-theoretic planning: Structural assumptions and computational leverage. JAIR, 11, 1\u201394.","journal-title":"JAIR"},{"key":"9268_CR6","unstructured":"Cannady, J. (2000). Next generation intrusion detection: Autonomous reinforcement learning of network attacks. In Proceedings of the 23rd National Information Systems Secuity Conference (pp. 1\u201312)."},{"key":"9268_CR7","doi-asserted-by":"crossref","unstructured":"Castelletti, A., Galelli, S., Restelli, M., & Soncini-Sessa, R. (2011). Tree-based variable selection for dimensionality reduction of large-scale control systems. In IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), IEEE (pp. 62\u201369).","DOI":"10.1109\/ADPRL.2011.5967387"},{"key":"9268_CR8","doi-asserted-by":"crossref","unstructured":"Cliff, D., & Miller, G. (1995). Racking the red queen: Measurements of adaptive progress in co-evolutionary simulations. In F. Morn, A. Moreno, J. Merelo, & P. Chacn (Eds.), Advances in artificial life, lecture notes in computer science (Vol. 929, pp. 200\u2013218). Berlin Heidelberg: Springer. doi: 10.1007\/3-540-59496-5_300","DOI":"10.1007\/3-540-59496-5_300"},{"key":"9268_CR9","unstructured":"Deisenroth, M., & Rasmussen, C. (2011). Pilco: A model-based and data-efficient approach to policy search. In L. Getoor & T. Scheffer (Eds.), Proceedings of the 28th International Conference on Machine Learning (ICML-11) (pp. 465\u2013472). New York: ACM."},{"key":"9268_CR10","volume-title":"Pattern recognition: A statistical approach","author":"P Devijver","year":"1982","unstructured":"Devijver, P., & Kittler, J. (1982). Pattern recognition: A statistical approach. London: Prentice Hall International."},{"key":"9268_CR11","unstructured":"Dietterich, T. G. (1998). The maxq method for hierarchical reinforcement learning. In Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann (pp. 118\u2013126)."},{"key":"9268_CR12","first-page":"249","volume-title":"Proceedings of the 26th International Conference on Machine Learning","author":"C Diuk","year":"2009","unstructured":"Diuk, C., Li, L., & Leffler, B. (2009). The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning. In L. Bottou & M. Littman (Eds.), Proceedings of the 26th International Conference on Machine Learning (pp. 249\u2013256). Montreal: Omnipress."},{"key":"9268_CR13","doi-asserted-by":"crossref","unstructured":"Doroodgar, B., & Nejat, G. (2010). A hierarchical reinforcement learning based control architecture for semi-autonomous rescue robots in cluttered environments. In 2010 IEEE Conference on Automation Science and Engineering (CASE) (pp. 948\u2013953).","DOI":"10.1109\/COASE.2010.5584599"},{"key":"9268_CR14","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., & Wehenkel, L. (2005). Tree-based batch mode reinforcement learning. JMLR, 6, 503\u2013556.","journal-title":"JMLR"},{"key":"9268_CR15","first-page":"41","volume-title":"Proceedings of the Second International Conference on Genetic Algorithms on Genetic Algorithms and Their Application","author":"DE Goldberg","year":"1987","unstructured":"Goldberg, D. E., & Richardson, J. (1987). Genetic algorithms with sharing for multimodal function optimization. Proceedings of the Second International Conference on Genetic Algorithms on Genetic Algorithms and Their Application (pp. 41\u201349). Hillsdale, NJ: L. Erlbaum Associates Inc."},{"key":"9268_CR16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1177\/105971239700500305","volume":"5","author":"F Gomez","year":"1997","unstructured":"Gomez, F., & Miikkulainen, R. (1997). Incremental evolution of complex general behavior. Adaptive Behavior, 5, 5\u2013317.","journal-title":"Adaptive Behavior"},{"key":"9268_CR17","unstructured":"Gomez, F. J., & Miikkulainen, R. (1999). Solving non-markovian control tasks with neuroevolution. In Proceedings of the 16th International Joint Conference on Artificial Intelligence, Morgan Kaufmann (pp. 1356\u20131361)."},{"key":"9268_CR18","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157\u20131182.","journal-title":"Journal of Machine Learning Research"},{"key":"9268_CR19","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","volume":"46","author":"I Guyon","year":"2002","unstructured":"Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene selection for cancer classification using support vector machines. Machine Learning, 46, 389\u2013422.","journal-title":"Machine Learning"},{"key":"9268_CR20","doi-asserted-by":"crossref","unstructured":"Hachiya, H., & Sugiyama, M. (2010). Feature selection for reinforcement learning: Evaluating implicit state-reward dependency via conditional mutual information. In Proceedings of the ECML (pp. 474\u2013489).","DOI":"10.1007\/978-3-642-15880-3_36"},{"key":"9268_CR21","unstructured":"Hall, M. (1999). Correlation based feature selection for machine learning. PhD thesis, University of Waikato, Department of Computer Science."},{"key":"9268_CR22","volume-title":"Principal component analysis","author":"IT Jolliffe","year":"2010","unstructured":"Jolliffe, I. T. (2010). Principal component analysis (2nd ed.). New York: Springer.","edition":"2"},{"key":"9268_CR23","doi-asserted-by":"crossref","unstructured":"Jung, T., & Stone, P. (2009). Feature selection for value function approximation using bayesian model selection. In Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 660\u2013675).","DOI":"10.1007\/978-3-642-04180-8_60"},{"key":"9268_CR24","doi-asserted-by":"crossref","unstructured":"Knowles, J. D., Watson, R. A., & Corne, D. W. (2001). Reducing local optima in single-objective problems by multi-objectivization. In E. Zitzler, L. Thiele, K. Deb, C. Coello Coello, & D. Corne (Eds.), Evolutionary multi-criterion optimization, lecture notes in computer science (Vol. 1993, pp. 269\u2013283). Berlin Heidelberg: Springer. doi: 10.1007\/3-540-44719-9_19","DOI":"10.1007\/3-540-44719-9_19"},{"key":"9268_CR25","doi-asserted-by":"crossref","unstructured":"Kolter, J. Z., & Ng, A. Y. (2009). Regularization and feature selection in least-squares temporal difference learning. In Proceedings of the 26th Annual International Conference on Machine Learning (pp. 521\u2013528).","DOI":"10.1145\/1553374.1553442"},{"key":"9268_CR26","first-page":"1107","volume-title":"Proceedings of the 21st International Jont Conference on Artifical Intelligence","author":"G Konidaris","year":"2009","unstructured":"Konidaris, G., & Barto, A. (2009). Efficient skill learning using abstraction selection. Proceedings of the 21st International Jont Conference on Artifical Intelligence (pp. 1107\u20131112). San Francisco, CA: Morgan Kaufmann Publishers Inc."},{"key":"9268_CR27","first-page":"1162","volume":"23","author":"G Konidaris","year":"2010","unstructured":"Konidaris, G., Kuindersma, S., Barto, A., & Grupen, R. (2010). Constructing skill trees for reinforcement learning agents from demonstration trajectories. NIPS, 23, 1162\u20131170.","journal-title":"NIPS"},{"key":"9268_CR28","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1613\/jair.2085","volume":"27","author":"B Kveton","year":"2006","unstructured":"Kveton, B., Hauskrecht, M., & Guestrin, C. (2006). Solving factored MDPs with hybrid state and action variables. Journal of Artificial Intelligence Research, 27, 153\u2013201.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9268_CR29","first-page":"833","volume-title":"Advances in Neural Information Processing Systems","author":"A Lazaric","year":"2007","unstructured":"Lazaric, A., Restelli, M., & Bonarini, A. (2007). Reinforcement learning in continuous action spaces through sequential monte carlo methods. Advances in Neural Information Processing Systems (pp. 833\u2013840). Cambridge: MIT Press."},{"issue":"2","key":"9268_CR30","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1162\/EVCO_a_00025","volume":"19","author":"J Lehman","year":"2011","unstructured":"Lehman, J., & Stanley, K. O. (2011). Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation, 19(2), 189\u2013223.","journal-title":"Evolutionary Computation"},{"key":"9268_CR31","unstructured":"Li, L., Walsh, T. J., & Littman, M. L. (2006). Towards a unified theory of state abstraction for MDPs. In Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics (pp. 531\u2013539)."},{"issue":"4","key":"9268_CR32","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1109\/TKDE.2005.66","volume":"17","author":"H Liu","year":"2005","unstructured":"Liu, H., & Yu, L. (2005). Toward integrating feature selection algorithms for classification and clustering. IEEE Transactions on Knowledge and Data Engineering, 17(4), 491\u2013502.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"9268_CR33","doi-asserted-by":"crossref","unstructured":"Loscalzo, S., Wright, R., Acunto, K., & Yu, L. (2012). Sample aware embedded feature selection for reinforcement learning. In Proceedings of GECCO (pp. 879\u2013886).","DOI":"10.1145\/2330163.2330286"},{"key":"9268_CR34","first-page":"372","volume-title":"Proceedings of the Proceedings of the Twenty-First Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-05)","author":"S Mahadevan","year":"2005","unstructured":"Mahadevan, S. (2005). Representation policy iteration. Proceedings of the Proceedings of the Twenty-First Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-05) (pp. 372\u2013379). Arlington, Virginia: AUAI Press."},{"issue":"1","key":"9268_CR35","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1287\/orsc.2.1.71","volume":"2","author":"JG March","year":"1991","unstructured":"March, J. G. (1991). Exploration and exploitation in organizational learning. Organizational Science, 2(1), 71\u201387.","journal-title":"Organizational Science"},{"key":"9268_CR36","doi-asserted-by":"crossref","unstructured":"Melo, F. S., & Lopes, M. (2008). Fitted natural actor-critic: A new algorithm for continuous state-action MDPs. In ECML\/PKDD(2) (pp. 66\u201381).","DOI":"10.1007\/978-3-540-87481-2_5"},{"issue":"1","key":"9268_CR37","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1162\/EVCO_a_00048","volume":"20","author":"JB Mouret","year":"2012","unstructured":"Mouret, J. B., & Doncieux, S. (2012). Encouraging behavioral diversity in evolutionary robotics: An empirical study. Evolutionary Computation, 20(1), 91\u2013133. doi: 10.1162\/EVCO_a_00048 .","journal-title":"Evolutionary Computation"},{"key":"9268_CR38","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/s10994-010-5202-y","volume":"81","author":"A Nouri","year":"2010","unstructured":"Nouri, A., & Littman, M. (2010). Dimension reduction and its application to model-based exploration in continuous spaces. Machine Learning, 81, 85\u201398.","journal-title":"Machine Learning"},{"key":"9268_CR39","doi-asserted-by":"crossref","unstructured":"Parr, R., Painter-Wakefield, C., Li, L., & Littman, M.L. (2007). Analyzing feature generation for value-function approximation. In ICML (pp. 737\u2013744).","DOI":"10.1145\/1273496.1273589"},{"key":"9268_CR40","doi-asserted-by":"crossref","unstructured":"Pazis, J., & Lagoudakis, M. G. (2009). Binary action search for learning continuous-action control policies. In Proceedings of the 26th Annual International Conference on Machine Learning ICML \u201909 (pp. 793\u2013800). New York: ACM.","DOI":"10.1145\/1553374.1553476"},{"key":"9268_CR41","unstructured":"Petrik, M., Taylor, G., Parr, R., & Zilberstein, S. (2010). Feature selection using regularization in approximate linear programs for markov decision processes. In Proceedings of the 27th International Conference on Machine Learning (pp. 871\u2013878)."},{"key":"9268_CR42","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029176","volume-title":"Approximate dynamic programming: Solving the curses of dimensionality","author":"WB Powell","year":"2011","unstructured":"Powell, W. B. (2011). Approximate dynamic programming: Solving the curses of dimensionality (2nd ed.). Hoboken, NJ: Wiley.","edition":"2"},{"key":"9268_CR43","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"ML Puterman","year":"1994","unstructured":"Puterman, M. L. (1994). Markov decision processes: Discrete stochastic dynamic programming. New York: Wiley-Interscience."},{"key":"9268_CR44","doi-asserted-by":"crossref","unstructured":"Servin, A., & Kudenko, D. (2008). Multi-agent reinforcement learning for intrusion detection: A case study and evaluation. In Proceedings of the European Conference on Artificial Intelligence (pp. 873\u2013874).","DOI":"10.1007\/978-3-540-87805-6_15"},{"key":"9268_CR45","volume-title":"Handbook of neuroevolution through Erlang","author":"GI Sher","year":"2012","unstructured":"Sher, G. I. (2012). Handbook of neuroevolution through Erlang. New York: Springer."},{"key":"9268_CR46","unstructured":"Stanley, K. O., & Miikkulainen, R. (2002). Efficient reinforcement learning through evolving neural network topologies. In Proceedings of GECCO (pp. 569\u2013577)."},{"key":"9268_CR47","volume-title":"Reinforcement learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press."},{"issue":"4","key":"9268_CR48","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s12065-009-0018-z","volume":"1","author":"M Tan","year":"2009","unstructured":"Tan, M., Hartley, M., Bister, M., & Deklerck, R. (2009). Automated feature selection in neuroevolution. Evolutionary Intelligence, 1(4), 271\u2013292.","journal-title":"Evolutionary Intelligence"},{"key":"9268_CR49","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1145\/2330784.2330869","volume-title":"GECCO (Companion)","author":"M Tan","year":"2012","unstructured":"Tan, M., Deklerck, R., Jansen, B., & Cornelis, J. (2012). Analysis of a feature-deselective neuroevolution classifier (FD-NEAT) in a computer-aided lung nodule detection system for ct images. In T. Soule & J. H. Moore (Eds.), GECCO (Companion) (pp. 539\u2013546). New York: ACM."},{"key":"9268_CR50","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M. E., & Stone, P. (2009). Transfer learning for reinforcement learning domains: A survey. JMLR, 10, 1633\u20131685.","journal-title":"JMLR"},{"key":"9268_CR51","unstructured":"Tesauro, G., Das, R., Chan, H., Kephart, J. O., Levine, D., III FLR, & Lefurgy, C. (2007). Managing power consumption and performance of computing systems using reinforcement learning. In NIPS."},{"key":"9268_CR52","volume-title":"Incremental structure learning in factored MDPs with continuous states and actions","author":"CM Vigorito","year":"2009","unstructured":"Vigorito, C. M., & Barto, A. G. (2009). Incremental structure learning in factored MDPs with continuous states and actions. Tech. rep.: University of Massachusetts Amherst - Department of Computer Science."},{"key":"9268_CR53","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C. J. C. H., & Dayan, P. (1992). Technical note q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"},{"key":"9268_CR54","first-page":"877","volume":"7","author":"S Whiteson","year":"2006","unstructured":"Whiteson, S., & Stone, P. (2006). Evolutionary function approximation for reinforcement learning. Journal of Machine Learning Research, 7, 877\u2013917.","journal-title":"Journal of Machine Learning Research"},{"key":"9268_CR55","doi-asserted-by":"crossref","unstructured":"Whiteson, S., Stone, P., & Stanley, K. O. (2005). Automatic feature selection in neuroevolution. In Proceedings of GECCO (pp. 1225\u20131232).","DOI":"10.1145\/1068009.1068210"},{"key":"9268_CR56","unstructured":"Wright, R., Loscalzo, S., & Yu, L. (2011). Embedded incremental feature selection for reinforcement learning. In ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence, Artificial Intelligence, Rome, Italy, January 28\u201330 (Vol. 1, pp. 263\u2013268)."},{"key":"9268_CR57","unstructured":"Xu, L., Yan, P., & Chang, T. (1988). Best first strategy for feature selection. In Proceedings of the Ninth International Conference on Pattern Recognition (pp. 706\u2013708)."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-014-9268-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-014-9268-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-014-9268-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T15:50:53Z","timestamp":1565625053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-014-9268-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,10]]},"references-count":57,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2015,9]]}},"alternative-id":["9268"],"URL":"https:\/\/doi.org\/10.1007\/s10458-014-9268-y","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,10]]}}}