{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T04:16:34Z","timestamp":1742703394339,"version":"3.40.2"},"publisher-location":"Berlin, Heidelberg","reference-count":51,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642276446"},{"type":"electronic","value":"9783642276453"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-27645-3_13","type":"book-chapter","created":{"date-parts":[[2012,3,5]],"date-time":"2012-03-05T22:18:12Z","timestamp":1330985892000},"page":"415-439","source":"Crossref","is-referenced-by-count":2,"title":["Predictively Defined Representations of State"],"prefix":"10.1007","author":[{"given":"David","family":"Wingate","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"13_CR1","unstructured":"Aberdeen, D., Buffet, O., Thomas, O.: Policy-gradients for psrs and pomdps. In: International Workshop on Artificial Intelligence and Statistics, AISTAT (2007)"},{"key":"13_CR2","first-page":"174","volume":"10","author":"K.J. Astrom","year":"1965","unstructured":"Astrom, K.J.: Optimal control of Markov decision processes with the incomplete state estimation. Journal of Computer and System Sciences\u00a010, 174\u2013205 (1965)","journal-title":"Journal of Computer and System Sciences"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Boots, B., Siddiqi, S., Gordon, G.: Closing the learning-planning loop with predictive state representations. In: Proceedings of Robotics: Science and Systems VI, RSS (2010)","DOI":"10.15607\/RSS.2010.VI.036"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Boularias, A., Chaib-draa, B.: Predictive representations for policy gradient in pomdps. In: International Conference on Machine Learning, ICML (2009)","DOI":"10.1145\/1553374.1553383"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Bowling, M., McCracken, P., James, M., Neufeld, J., Wilkinson, D.: Learning predictive state representations using non-blind policies. In: International Conference on Machine Learning (ICML), pp. 129\u2013136 (2006)","DOI":"10.1145\/1143844.1143861"},{"key":"13_CR6","unstructured":"Ghahramani, Z., Hinton, G.E.: Parameter estimation for linear dynamical systems. Tech. Rep. CRG-TR-96-2, Dept. of Computer Science, U. of Toronto (1996)"},{"key":"13_CR7","unstructured":"Izadi, M., Precup, D.: Model minimization by linear psr. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1749\u20131750 (2005)"},{"key":"13_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-540-68825-9_13","volume-title":"Advances in Artificial Intelligence","author":"M.T. Izadi","year":"2008","unstructured":"Izadi, M.T., Precup, D.: Point-Based Planning for Predictive State Representations. In: Bergler, S. (ed.) Canadian AI. LNCS (LNAI), vol.\u00a05032, pp. 126\u2013137. Springer, Heidelberg (2008)"},{"issue":"6","key":"13_CR9","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1162\/089976600300015411","volume":"12","author":"H. Jaeger","year":"2000","unstructured":"Jaeger, H.: Observable operator processes and conditioned continuation representations. Neural Computation\u00a012(6), 1371\u20131398 (2000)","journal-title":"Neural Computation"},{"key":"13_CR10","unstructured":"Jaeger, H.: Discrete-time, discrete-valued observable operator models: A tutorial. Tech. rep., International University Bremen (2004)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"James, M., Singh, S., Littman, M.: Planning with predictive state representations. In: International Conference on Machine Learning and Applications (ICMLA), pp. 304\u2013311 (2004)","DOI":"10.1109\/ICMLA.2004.1383528"},{"key":"13_CR12","unstructured":"James, M., Wessling, T., Vlassis, N.: Improving approximate value iteration using memories and predictive state representations. In: Proceedings of AAAI (2006)"},{"key":"13_CR13","unstructured":"James, M.R.: Using predictions for planning and modeling in stochastic environments. PhD thesis, University of Michigan (2005)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"James, M.R., Singh, S.: Learning and discovery of predictive state representations in dynamical systems with reset. In: International Conference on Machine Learning (ICML), pp. 417\u2013424 (2004)","DOI":"10.1145\/1015330.1015359"},{"key":"13_CR15","unstructured":"James, M.R., Singh, S.: Planning in models that combine memory with predictive representations of state. In: National Conference on Artificial Intelligence (AAAI), pp. 987\u2013992 (2005a)"},{"key":"13_CR16","unstructured":"James, M.R., Wolfe, B., Singh, S.: Combining memory and landmarks with predictive state representations. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 734\u2013739 (2005b)"},{"issue":"Series D","key":"13_CR17","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82","author":"R.E. Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problem. Transactions of the ASME\u2014Journal of Basic Engineering\u00a082(Series D), 35\u201345 (1960)","journal-title":"Transactions of the ASME\u2014Journal of Basic Engineering"},{"key":"13_CR18","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 (JMLR)\u00a04, 1107\u20131149 (2003)","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"13_CR19","unstructured":"Littman, M.L., Sutton, R.S., Singh, S.: Predictive representations of state. In: Neural Information Processing Systems (NIPS), pp. 1555\u20131561 (2002)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"McCracken, P., Bowling, M.: Online discovery and learning of predictive state representations. In: Neural Information Processings Systems (NIPS), pp. 875\u2013882 (2006)","DOI":"10.1145\/1143844.1143861"},{"key":"13_CR21","unstructured":"Nikovski, D.: State-aggregation algorithms for learning probabilistic models for robot control. PhD thesis, Carnegie Mellon University (2002)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Peters, J., Vijayakumar, S., Schaal, S.: Natural actor-critic. In: European Conference on Machine Learning (ECML), pp. 280\u2013291 (2005)","DOI":"10.1007\/11564096_29"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Precup, D., Sutton, R.S., Singh, S.: Theoretical results on reinforcement learning with temporally abstract options. In: European Conference on Machine Learning (ECML), pp. 382\u2013393 (1998)","DOI":"10.1007\/BFb0026709"},{"key":"13_CR24","unstructured":"Rafols, E.J., Ring, M.B., Sutton, R.S., Tanner, B.: Using predictive representations to improve generalization in reinforcement learning. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 835\u2013840 (2005)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Rivest, R.L., Schapire, R.E.: Diversity-based inference of finite automata. In: IEEE Symposium on the Foundations of Computer Science, pp. 78\u201387 (1987)","DOI":"10.1109\/SFCS.1987.21"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Rosencrantz, M., Gordon, G., Thrun, S.: Learning low dimensional predictive representations. In: International Conference on Machine Learning (ICML), pp. 695\u2013702 (2004)","DOI":"10.1145\/1015330.1015441"},{"key":"13_CR27","unstructured":"Rudary, M., Singh, S.: Predictive linear-Gaussian models of stochastic dynamical systems with vector-value actions and observations. In: Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics, ISAIM (2008)"},{"key":"13_CR28","unstructured":"Rudary, M.R., Singh, S.: A nonlinear predictive state representation. Neural Information Processing Systems (NIPS), 855\u2013862 (2004)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Rudary, M.R., Singh, S.: Predictive linear-Gaussian models of controlled stochastic dynamical systems. In: International Conference on Machine Learning (ICML), pp. 777\u2013784 (2006)","DOI":"10.1145\/1143844.1143942"},{"key":"13_CR30","unstructured":"Rudary, M.R., Singh, S., Wingate, D.: Predictive linear-Gaussian models of stochastic dynamical systems. In: Uncertainty in Artificial Intelligence, pp. 501\u2013508 (2005)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Shatkay, H., Kaelbling, L.P.: Learning geometrically-constrained hidden Markov models for robot navigation: Bridging the geometrical-topological gap. Journal of AI Research (JAIR), 167\u2013207 (2002)","DOI":"10.1613\/jair.874"},{"key":"13_CR32","unstructured":"Singh, S., Littman, M., Jong, N., Pardoe, D., Stone, P.: Learning predictive state representations. In: International Conference on Machine Learning (ICML), pp. 712\u2013719 (2003)"},{"key":"13_CR33","unstructured":"Singh, S., James, M.R., Rudary, M.R.: Predictive state representations: A new theory for modeling dynamical systems. In: Uncertainty in Artificial Intelligence (UAI), pp. 512\u2013519 (2004)"},{"key":"13_CR34","unstructured":"Sutton, R.S., Tanner, B.: Temporal-difference networks. In: Neural Information Processing Systems (NIPS), pp. 1377\u20131384 (2005)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Tanner, B., Sutton, R.: Td(lambda) networks: Temporal difference networks with eligibility traces. In: International Conference on Machine Learning (ICML), pp. 888\u2013895 (2005a)","DOI":"10.1145\/1102351.1102463"},{"key":"13_CR36","unstructured":"Tanner, B., Sutton, R.: b) Temporal difference networks with history. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 865\u2013870 (2005)"},{"key":"13_CR37","unstructured":"Tanner, B., Bulitko, V., Koop, A., Paduraru, C.: Grounding abstractions in predictive state representations. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1077\u20131082 (2007)"},{"key":"13_CR38","unstructured":"Wan, E.A., van der Merwe, R.: The unscented Kalman filter for nonlinear estimation. In: Proceedings of Symposium 2000 on Adaptive Systems for Signal Processing, Communication and Control (2000)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Wiewiora, E.: Learning predictive representations from a history. In: International Conference on Machine Learning (ICML), pp. 964\u2013971 (2005)","DOI":"10.1145\/1102351.1102473"},{"key":"13_CR40","unstructured":"Wingate, D.: Exponential family predictive representations of state. PhD thesis, University of Michigan (2008)"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Wingate, D., Singh, S.: Kernel predictive linear Gaussian models for nonlinear stochastic dynamical systems. In: International Conference on Machine Learning (ICML), pp. 1017\u20131024 (2006a)","DOI":"10.1145\/1143844.1143972"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Wingate, D., Singh, S.: Mixtures of predictive linear Gaussian models for nonlinear stochastic dynamical systems. In: National Conference on Artificial Intelligence (AAAI) (2006b)","DOI":"10.1145\/1143844.1143972"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Wingate, D., Singh, S.: Exponential family predictive representations of state. In: Neural Information Processing Systems, NIPS (2007a) (to appear)","DOI":"10.1145\/1390156.1390304"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Wingate, D., Singh, S.: On discovery and learning of models with predictive representations of state for agents with continuous actions and observations. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 1128\u20131135 (2007b)","DOI":"10.1145\/1329125.1329352"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Wingate, D., Singh, S.: Efficiently learning linear-linear exponential family predictive representations of state. In: International Conference on Machine Learning, ICML (2008)","DOI":"10.1145\/1390156.1390304"},{"key":"13_CR46","unstructured":"Wingate, D., Soni, V., Wolfe, B., Singh, S.: Relational knowledge with predictive representations of state. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 2035\u20132040 (2007)"},{"key":"13_CR47","unstructured":"Wolfe, B.: Modeling dynamical systems with structured predictive state representations. PhD thesis, University of Michigan (2009)"},{"key":"13_CR48","unstructured":"Wolfe, B.: Valid parameters for predictive state representations. In: Eleventh International Symposium on Artificial Intelligence and Mathematics (ISAIM) (2010)"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Wolfe, B., James, M.R., Singh, S.: Learning predictive state representations in dynamical systems without reset. In: International Conference on Machine Learning, pp. 980\u2013987 (2005)","DOI":"10.1145\/1102351.1102475"},{"key":"13_CR50","unstructured":"Wolfe, B., James, M., Singh, S.: Approximate predictive state representations. In: Procedings of the 2008 International Conference on Autonomous Agents and Multiagent Systems (AAMAS) (2008)"},{"key":"13_CR51","unstructured":"Wolfe, B., James, M., Singh, S.: Modeling multiple-mode systems with predictive state representations. In: Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems (2010)"}],"container-title":["Adaptation, Learning, and Optimization","Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-27645-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T13:02:08Z","timestamp":1742648528000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-27645-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642276446","9783642276453"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-27645-3_13","relation":{},"ISSN":["1867-4534","1867-4542"],"issn-type":[{"type":"print","value":"1867-4534"},{"type":"electronic","value":"1867-4542"}],"subject":[],"published":{"date-parts":[[2012]]}}}