{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T09:10:06Z","timestamp":1726477806665},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642319501"},{"type":"electronic","value":"9783642319518"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31951-8_2","type":"book-chapter","created":{"date-parts":[[2012,7,21]],"date-time":"2012-07-21T00:56:20Z","timestamp":1342832180000},"page":"2-6","source":"Crossref","is-referenced-by-count":2,"title":["Beyond Reward: The Problem of Knowledge and Data"],"prefix":"10.1007","author":[{"given":"Richard S.","family":"Sutton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Baird, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"2_CR2","unstructured":"Degris, T., Modayil, J.: Scaling-up knowledge for a cognizant robot. In: Notes of the AAAI Spring Symposium on Designing Intelligent Robots: Reintegrating AI (2012)"},{"key":"2_CR3","unstructured":"Konidaris, G., Barto, A.G.: Building portable options: Skill transfer in reinforcement learning. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence, pp. 895\u2013900 (2007)"},{"key":"2_CR4","unstructured":"Koop, A.: Investigating Experience: Temporal Coherence and Empirical Knowledge Representation. MSc. thesis, University of Alberta (2007)"},{"key":"2_CR5","unstructured":"Maei, H.R.: Gradient Temporal-Difference Learning Algorithms. PhD. thesis, University of Alberta (2011)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Maei, H.R., Sutton, R.S.: GQ(\u03bb): A general gradient algorithm for temporal-difference prediction learning with eligibility traces. In: Proceedings of the Third Conference on Artificial General Intelligence (2010)","DOI":"10.2991\/agi.2010.22"},{"key":"2_CR7","unstructured":"Maei, H.R., Szepesv\u00e1ri, C., Bhatnagar, S., Precup, D., Silver, D., Sutton, R.S.: Convergent temporal-difference learning with arbitrary smooth function approximation. In: Advances in Neural Information Processing Systems, vol.\u00a022. MIT Press (2009)"},{"key":"2_CR8","unstructured":"Maei, H.R., Szepesv\u00e1ri, C., Bhatnagar, S., Sutton, R.S.: Toward off-policy learning control with function approximation. In: Proceedings of the 27th International Conference on Machine Learning (2010)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Mannor, S., Menache, I., Hoze, A., Klein, U.: Dynamic abstraction in reinforcement learning via clustering. In: Proceedings of the Twenty-First International Conference on Machine Learning (2004)","DOI":"10.1145\/1015330.1015355"},{"key":"2_CR10","unstructured":"McGovern, A., Sutton, R.S.: Macro-actions in reinforcement learning: An empirical analysis. Technical Report 98-70, University of Massachusetts, Department of Computer Science (1998)"},{"key":"2_CR11","unstructured":"Modayil, J., White, A., Sutton, R.S.: Multi-timescale nexting in a reinforcement learning robot. In: Proceedings of the 2012 Conference on Simulation of Adaptive Behaviour (to appear, 2012)"},{"key":"2_CR12","unstructured":"Parr, R.: Hierarchical Control and Learning for Markov Decision Processes. PhD thesis, University of California at Berkeley (1998)"},{"key":"2_CR13","unstructured":"Precup, D.: Temporal Abstraction in Reinforcement Learning. PhD thesis, University of Massachusetts (2000)"},{"key":"2_CR14","unstructured":"Rafols, E.J.: Temporal Abstraction in Temporal-difference Networks. MSc. thesis, University of Alberta (2006)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Singh, S., Barto, A.G., Chentanez, N.: Intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems, vol.\u00a017, pp. 1281\u20131288 (2005)","DOI":"10.21236\/ADA440280"},{"key":"2_CR16","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/3-540-45622-8_16","volume-title":"Abstraction, Reformulation, and Approximation","author":"M. Stolle","year":"2002","unstructured":"Stolle, M., Precup, D.: Learning Options in Reinforcement Learning. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS (LNAI), vol.\u00a02371, pp. 212\u2013223. Springer, Heidelberg (2002)"},{"key":"2_CR17","unstructured":"Sutton, R.S.: \u201cVerification\u201d and \u201cVerfication, the key to AI\u201d (2001), \n                    \n                      http:\/\/richsutton.com\/IncIdeas\/Verification.html\n                    \n                    \n                  , \n                    \n                      http:\/\/richsutton.com\/IncIdeas\/KeytoAI.html"},{"key":"2_CR18","unstructured":"Sutton, R.S.: The grand challenge of predictive empirical abstract knowledge. In: Working Notes of the IJCAI 2009 Workshop on Grand Challenges for Reasoning from Experiences (2009)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Maei, H.R., Precup, D., Bhatnagar, S., Silver, D., Szepesv\u00e1ri, C., Wiewiora, E.: Fast gradient-descent methods for temporal-difference learning with linear function approximation. In: Proceedings of the 26th International Conference on Machine Learning (2009)","DOI":"10.1145\/1553374.1553501"},{"key":"2_CR21","unstructured":"Sutton, R.S., Modayil, J., Delp, M., Degris, T., Pilarski, P.M., White, A., Precup, D.: Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In: Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems, AAMAS (2011)"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R.S. Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112, 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Szepesv\u00e1ri, C., Maei, H.R.: A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation. In: Advances in Neural Information Processing Systems, vol.\u00a021. MIT Press (2009)","DOI":"10.1145\/1553374.1553501"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An analysis of temporal-difference learning with function approximation. IEEE Transactions on Automatic Control\u00a042, 674\u2013690 (1997)","journal-title":"IEEE Transactions on Automatic Control"}],"container-title":["Lecture Notes in Computer Science","Inductive Logic Programming"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31951-8_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T11:51:59Z","timestamp":1620129119000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31951-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642319501","9783642319518"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31951-8_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}