{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:36:44Z","timestamp":1775608604041,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,4,9]],"date-time":"2013-04-09T00:00:00Z","timestamp":1365465600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2013,7]]},"DOI":"10.1007\/s10994-013-5340-0","type":"journal-article","created":{"date-parts":[[2013,4,8]],"date-time":"2013-04-08T18:40:16Z","timestamp":1365446416000},"page":"5-39","source":"Crossref","is-referenced-by-count":79,"title":["A reinforcement learning approach to autonomous decision-making in smart electricity markets"],"prefix":"10.1007","volume":"92","author":[{"given":"Markus","family":"Peters","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Ketter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maytal","family":"Saar-Tsechansky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Collins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,4,9]]},"reference":[{"issue":"4","key":"5340_CR1","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1287\/isre.1100.0316","volume":"21","author":"M. Bichler","year":"2010","unstructured":"Bichler, M., Gupta, A., & Ketter, W. (2010). Designing smart markets. Information Systems Research, 21(4), 688\u2013699.","journal-title":"Information Systems Research"},{"issue":"1","key":"5340_CR2","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","volume":"7","author":"C. Bishop","year":"1995","unstructured":"Bishop, C. (1995). Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7(1), 108\u2013116.","journal-title":"Neural Computation"},{"issue":"1","key":"5340_CR3","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0004-3702(97)00063-5","volume":"97","author":"A. Blum","year":"1997","unstructured":"Blum, A., & Langley, P. (1997). Selection of relevant features and examples in machine learning. Artificial Intelligence, 97(1), 245\u2013271.","journal-title":"Artificial Intelligence"},{"issue":"1","key":"5340_CR4","first-page":"33","volume":"22","author":"S. Bradtke","year":"1996","unstructured":"Bradtke, S., & Barto, A. (1996). Linear least-squares algorithms for temporal difference learning. Machine Learning, 22(1), 33\u201357.","journal-title":"Machine Learning"},{"key":"5340_CR5","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","volume-title":"Reinforcement learning and dynamic programming using function approximators","author":"L. Busoniu","year":"2010","unstructured":"Busoniu, L., Babuska, R., De Schutter, B., & Ernst, D. (2010). Reinforcement learning and dynamic programming using function approximators. Boca Raton: CRC."},{"issue":"3","key":"5340_CR6","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.ijforecast.2004.12.005","volume":"21","author":"A. J. Conejo","year":"2005","unstructured":"Conejo, A. J., Contreras, J., & Plazas, M. A. (2005). Forecasting electricity prices for a day-ahead pool-based electric energy market. International Journal of Forecasting, 21(3), 435\u2013462.","journal-title":"International Journal of Forecasting"},{"issue":"6","key":"5340_CR7","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MIS.2003.1249168","volume":"18","author":"R. Dash","year":"2003","unstructured":"Dash, R., Jennings, N., & Parkes, D. (2003). Computational-mechanism design: a call to arms. IEEE Intelligent Systems, 18(6), 40\u201347.","journal-title":"IEEE Intelligent Systems"},{"issue":"2","key":"5340_CR8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1022606120092","volume":"3","author":"K. Jong De","year":"1988","unstructured":"De Jong, K. (1988). Learning with genetic algorithms: an overview. Machine Learning, 3(2), 121\u2013138.","journal-title":"Machine Learning"},{"key":"5340_CR9","first-page":"1","volume-title":"Conference on information systems and technology","author":"M. Weerdt de","year":"2011","unstructured":"de Weerdt, M., Ketter, W., & Collins, J. (2011). A theoretical analysis of pricing mechanisms and broker\u2019s decisions for real-time balancing in sustainable regional electricity markets. In Conference on information systems and technology, Charlotte (pp. 1\u201317)."},{"key":"5340_CR10","unstructured":"ETPSG (2010). European technology platform smart grids: strategic deployment document for Europe\u2019s electricity networks of the future."},{"key":"5340_CR11","unstructured":"European Commission (2011). EU energy country factsheet."},{"key":"5340_CR12","first-page":"721","volume-title":"Proceedings of the twenty-fourth annual conference on advances in neural information processing systems","author":"M. Ghavamzadeh","year":"2010","unstructured":"Ghavamzadeh, M., Lazaric, A., Maillard, O., & Munos, R. (2010). LSTD with random projections. In Proceedings of the twenty-fourth annual conference on advances in neural information processing systems (pp. 721\u2013729)."},{"key":"5340_CR13","doi-asserted-by":"crossref","first-page":"8163","DOI":"10.1016\/j.enpol.2011.10.016","volume":"39","author":"S. Gottwalt","year":"2011","unstructured":"Gottwalt, S., Ketter, W., Block, C., Collins, J., & Weinhardt, C. (2011). Demand side management\u2014a simulation of household behavior under variable prices. Energy Policy, 39, 8163\u20138174.","journal-title":"Energy Policy"},{"key":"5340_CR14","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"},{"issue":"1","key":"5340_CR15","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.energy.2006.01.014","volume":"32","author":"K. Herter","year":"2007","unstructured":"Herter, K., McAuliffe, P., & Rosenfeld, A. (2007). An exploratory analysis of California residential customer response to critical peak pricing of electricity. Energy, 32(1), 25\u201334.","journal-title":"Energy"},{"key":"5340_CR16","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1287\/isre.1110.0415","volume":"23","author":"W. Ketter","year":"2012","unstructured":"Ketter, W., Collins, J., Gini, M., Gupta, A., & Schrater, P. (2012a). Real-time tactical and strategic sales management for intelligent agents guided by economic regimes. Information Systems Research, 23, 1263\u20131283.","journal-title":"Information Systems Research"},{"key":"5340_CR17","unstructured":"Ketter, W., Collins, J., Reddy, P., & de Weerdt, M. (2012b). The 2012 power trading agent competition (Tech. Rep. ERS-2012-010-LIS). RSM Erasmus University, Rotterdam, The Netherlands. http:\/\/ssrn.com\/paper=2144644 ."},{"key":"5340_CR18","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1145\/1553374.1553442","volume-title":"Proceedings of the 26th annual international conference on machine learning","author":"J. Kolter","year":"2009","unstructured":"Kolter, J., & Ng, A. (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). New York: ACM."},{"key":"5340_CR19","first-page":"1107","volume":"4","author":"M. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M., & Parr, R. (2003). Least-squares policy iteration. Journal of Machine Learning Research, 4, 1107\u20131149.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"5340_CR20","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/BF02022092","volume":"21","author":"G. Liepins","year":"1989","unstructured":"Liepins, G.,& Hilliard, M. (1989). Genetic algorithms: foundations and applications. Annals of Operations Research, 21(1), 31\u201357.","journal-title":"Annals of Operations Research"},{"key":"5340_CR21","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/ADPRL.2007.368210","volume-title":"IEEE international symposium on approximate dynamic programming and reinforcement learning","author":"M. Loth","year":"2007","unstructured":"Loth, M., Davy, M., & Preux, P. (2007). Sparse temporal difference learning using LASSO. In IEEE international symposium on approximate dynamic programming and reinforcement learning (pp. 352\u2013359). New York: IEEE."},{"issue":"5","key":"5340_CR22","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/4235.956714","volume":"5","author":"J. Nicolaisen","year":"2001","unstructured":"Nicolaisen, J., Petrov, V., & Tesfatsion, L. (2001). Market power and efficiency in a computational electricity market with discriminatory double-auction pricing. IEEE Transactions on Evolutionary Computation, 5(5), 504\u2013523.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"5340_CR23","unstructured":"Painter-Wakefield, C., & Parr, R. (2012). L1 regularized linear temporal difference learning (Tech. Rep. TR-2012-01) Duke University, Computer Science."},{"issue":"3","key":"5340_CR24","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1287\/ijoc.1090.0353","volume":"22","author":"D. Pardoe","year":"2010","unstructured":"Pardoe, D., Stone, P., Saar-Tsechansky, M., Keskin, T., & Tomak, K. (2010). Adaptive auction mechanism design and the incorporation of prior knowledge. INFORMS Journal on Computing, 22(3), 353\u2013370.","journal-title":"INFORMS Journal on Computing"},{"key":"5340_CR25","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1017\/CBO9780511800481.018","volume-title":"Algorithmic game theory","author":"D. C. Parkes","year":"2007","unstructured":"Parkes, D. C. (2007). Online mechanisms. In Algorithmic game theory (pp. 411\u2013439). Cambridge: Cambridge University Press."},{"key":"5340_CR26","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1145\/1390156.1390251","volume-title":"Proceedings of the 25th international conference on machine learning","author":"R. Parr","year":"2008","unstructured":"Parr, R., Li, L., Taylor, G., Painter-Wakefield, C., & Littman, M. L. (2008). An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning. In Proceedings of the 25th international conference on machine learning (pp. 752\u2013759). New York: ACM."},{"key":"5340_CR27","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1007\/978-3-642-33486-3_9","volume-title":"Machine learning and knowledge discovery in databases","author":"M. Peters","year":"2012","unstructured":"Peters, M., Ketter, W., Saar-Tsechansky, M., & Collins, J. (2012). Autonomous data-driven decision-making in smart electricity markets. In P. Flach, T. Bie, & N. Cristianini (Eds.), Lecture notes in computer science: Vol.\u00a07524. Machine learning and knowledge discovery in databases (pp. 132\u2013147). Berlin: Springer."},{"key":"5340_CR28","volume-title":"International conference on machine learning (ICML)","author":"M. Petrik","year":"2010","unstructured":"Petrik, M., Taylor, G., Parr, R., & Zilberstein, S. (2010). Feature selection using regularization in approximate linear programs for Markov decision processes. In International conference on machine learning (ICML)."},{"key":"5340_CR29","first-page":"70","volume-title":"Proceedings of the third international symposium on adaptive systems: evolutionary computation and probabilistic graphical models","author":"L. Pyeatt","year":"2001","unstructured":"Pyeatt, L., Howe, A., et al. (2001). Decision tree function approximation in reinforcement learning. In Proceedings of the third international symposium on adaptive systems: evolutionary computation and probabilistic graphical models (Vol.\u00a02, pp. 70\u201377)."},{"issue":"5","key":"5340_CR30","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1109\/TSMCC.2010.2044174","volume":"40","author":"M. Rahimiyan","year":"2010","unstructured":"Rahimiyan, M., & Mashhadi, H. (2010). An adaptive Q-learning algorithm developed for agent-based computational modeling of electricity market. IEEE Transactions on Systems, Man and Cybernetics, 40(5), 547\u2013556.","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"key":"5340_CR31","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/978-3-642-33486-3_14","volume-title":"Machine learning and knowledge discovery in databases","author":"V. Ramavajjala","year":"2012","unstructured":"Ramavajjala, V., & Elkan, C. (2012). Policy iteration based on a learned transition model. In Machine learning and knowledge discovery in databases (pp. 211\u2013226)."},{"key":"5340_CR32","volume-title":"Proceedings of the twenty-fifth AAAI conference on artificial intelligence (AAAI-11)","author":"P. Reddy","year":"2011","unstructured":"Reddy, P., & Veloso, M. (2011a). Learned behaviors of multiple autonomous agents in smart grid markets. In Proceedings of the twenty-fifth AAAI conference on artificial intelligence (AAAI-11)."},{"key":"5340_CR33","first-page":"1446","volume-title":"Proceedings of the twenty-second international joint conference on artificial intelligence (IJCAI)","author":"P. Reddy","year":"2011","unstructured":"Reddy, P., & Veloso, M. (2011b). Strategy learning for autonomous agents in smart grid markets. In Proceedings of the twenty-second international joint conference on artificial intelligence (IJCAI) (pp.\u00a01446\u20131451)."},{"key":"5340_CR34","unstructured":"Rummery, G., & Niranjan, M. (1994). On-line Q-learning using connectionist systems. Tech. Rep. CUED\/F-INFENG\/TR 166, University of Cambridge."},{"key":"5340_CR35","volume-title":"Reinforcement learning: an introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning: an introduction (Vol.\u00a0116). Cambridge: Cambridge University Press."},{"issue":"1","key":"5340_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00268ED1V01Y201005AIM009","volume":"4","author":"C. Szepesv\u00e1ri","year":"2010","unstructured":"Szepesv\u00e1ri, C. (2010). Algorithms for reinforcement learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 4(1), 1\u2013103.","journal-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning"},{"key":"5340_CR37","first-page":"1","volume-title":"Power & energy society general meeting","author":"G. Venayagamoorthy","year":"2009","unstructured":"Venayagamoorthy, G. (2009). Potentials and promises of computational intelligence for smart grids. In Power & energy society general meeting (pp. 1\u20136). New York: IEEE."},{"key":"5340_CR38","first-page":"3356","volume-title":"International joint conference on neural networks","author":"P. Werbos","year":"2009","unstructured":"Werbos, P. (2009). Putting more brain-like intelligence into the electric power grid: what we need and how to do it. In International joint conference on neural networks (pp. 3356\u20133359). New York: IEEE."},{"key":"5340_CR39","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1145\/1068009.1068210","volume-title":"Proceedings of the 2005 conference on genetic and evolutionary computation","author":"S. Whiteson","year":"2005","unstructured":"Whiteson, S., Stone, P., Stanley, K., Miikkulainen, R., & Kohl, N. (2005). Automatic feature selection in neuroevolution. In Proceedings of the 2005 conference on genetic and evolutionary computation (pp.\u00a01225\u20131232). New York: ACM."},{"key":"5340_CR40","volume-title":"IEEE symposium on adaptive dynamic programming and reinforcement learning (ADPRL)","author":"S. Whiteson","year":"2011","unstructured":"Whiteson, S., Tanner, B., Taylor, M. E., & Stone, P. (2011). Protecting against evaluation overfitting in empirical reinforcement learning. In IEEE symposium on adaptive dynamic programming and reinforcement learning (ADPRL)."},{"issue":"4","key":"5340_CR41","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1093\/oep\/gpq006","volume":"62","author":"C. Wilson","year":"2010","unstructured":"Wilson, C., & Price, C. (2010). Do consumers switch to the best supplier? Oxford Economic Papers, 62(4), 647\u2013668.","journal-title":"Oxford Economic Papers"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-013-5340-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-013-5340-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-013-5340-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T21:57:40Z","timestamp":1688162260000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-013-5340-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,9]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,7]]}},"alternative-id":["5340"],"URL":"https:\/\/doi.org\/10.1007\/s10994-013-5340-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,9]]}}}