{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T14:15:12Z","timestamp":1761488112944},"publisher-location":"Berlin, Heidelberg","reference-count":37,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540708261"},{"type":"electronic","value":"9783540708292"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-70829-2_11","type":"book-chapter","created":{"date-parts":[[2008,9,5]],"date-time":"2008-09-05T15:46:08Z","timestamp":1220629568000},"page":"233-253","source":"Crossref","is-referenced-by-count":2,"title":["The Concept of Opposition and Its Use in Q-Learning and Q(\u03bb) Techniques"],"prefix":"10.1007","author":[{"given":"Maryam","family":"Shokri","sequence":"first","affiliation":[]},{"given":"H. R.","family":"Tizhoosh","sequence":"additional","affiliation":[]},{"given":"Mohamed S.","family":"Kamel","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"11_CR1","volume-title":"Introduction to Machine Learning","author":"E. Alpaydin","year":"2004","unstructured":"Alpaydin, E.: Introduction to Machine Learning. MIT Press, Cambridge (2004)"},{"key":"11_CR2","volume-title":"Emotionally Motivated Reinforcement Learning Based Controller","author":"A. Ayesh","year":"2004","unstructured":"Ayesh, A.: Emotionally Motivated Reinforcement Learning Based Controller. IEEE SMC, The Hague (2004)"},{"key":"11_CR3","unstructured":"Collins Cobuild English Dictionary, pp. 77\u201385. HarperCollins Publishers, Fulham Palace Road, London, England (2000)"},{"key":"11_CR4","unstructured":"Gadanho, S.: Reinforcement Learning in Autonomous Robots: An Empirical Investigation of the Role of Emotions, PhD Thesis, University of Edinburgh, Edinburgh (1999)"},{"key":"11_CR5","unstructured":"Goel, S.K.: Subgoal Discovery for Hierarchical Reinforcement learning Using Learned Policies, Department of Computer Science and Engineering, University of Texas at Arlington, TX, USA, Master of Science in Computer Science and Engineering (2003)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Humphrys, M.: Action Selection Methods Using Reinforcement Learning, PhD Theses, University of Cambridge (1997)","DOI":"10.7551\/mitpress\/3118.003.0018"},{"key":"11_CR7","unstructured":"Jaakkola, T., Singh, S.P., Jordan, M.I.: Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems. In: Advances in Neural Information Processing Systems, vol. 7 (1994)"},{"key":"11_CR8","unstructured":"Kaelbling, L.P.: Hierarchical Reinforcement Learning: Preliminary Results. In: Proceedings of the Tenth International Conference on Machine Learning (1993)"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"L.P. Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and Acting in Partially Observable Stochastic Domains. Artificial Intelligence\u00a0101, 99\u2013134 (1998)","journal-title":"Artificial Intelligence"},{"key":"11_CR10","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"11_CR11","unstructured":"Maclin, R., Shavlik, J., Torrey, L., Walker, T., Wild, E.: Giving Advice about Preferred Actions to Reinforcement Learners Via Knowledge-Based Kernel Regression. American Association for Artificial Intelligence (2005)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Mahadevan, S., Kaelbling, L.P.: The NSF Workshop on Reinforcement Learning: Summary and Observations. In: AI Magazine (1996)","DOI":"10.1007\/b102434"},{"key":"11_CR13","unstructured":"Mc Govern, A., Sutton, R.S.: Macro-Actions in Reinforcement Learning: An Empirical Analysis, University of Massachusetts, Amherst, Technical Report Number 98-70 (1998)"},{"key":"11_CR14","unstructured":"Merriam-Webster Online English Dictioinary, http:\/\/www.m-w.com"},{"key":"11_CR15","unstructured":"Morales, E.F.: Relational State Abstractions for Reinforcement Learning. In: Proceedings of the ICML 2004 workshop on Relational Reinforcement Learning, Banff, Canada (2004)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Peng, J., Williams, R.J.: Incremental Multi-Step Q-Learning. Machine Learning 22 (1996)","DOI":"10.1007\/BF00114731"},{"key":"11_CR17","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1007\/s00500-002-0192-8","volume":"6","author":"T.D. Pham","year":"2002","unstructured":"Pham, T.D.: Perception-Based Hidden Markov Models: A Theoretical Framework for Data Mining and Knowledge Discovery. Soft Computing\u00a06, 400\u2013405 (2002)","journal-title":"Soft Computing"},{"key":"11_CR18","first-page":"26706","volume":"E 67","author":"A. Potapov","year":"2003","unstructured":"Potapov, A., Ali, M.K.: Convergence of Reinforcement Learning Algorithms and Acceleration of Learning. Physical Review\u00a0E 67, 026706 (2003)","journal-title":"Physical Review"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Rahnamayan, S., Tizhoosh, H.R., Salama, M.: Opposition-Based Differential Evolution Algorithms. In: IEEE International Joint Conference on Neural Networks (IJCNN), IEEE World Congress on Computational Intelligence, Vancouver, July 16-21 (2006)","DOI":"10.1109\/CEC.2006.1688554"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Rahnamayan, S., Tizhoosh, H.R., Salama, M.: Opposition-Based Differential Evolution for Optimization of Noisy Problems. In: IEEE Congress on Evolutionary Computation, IEEE World Congress on Computational Intelligence, Vancouver, July 16-21 (2006)","DOI":"10.1109\/CEC.2006.1688534"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Rahnamayn, S., Tizhoosh, H.R., Salama, M.: A Novel Population Initialization Method for Accelerating Evolutionary Algorithms. In: Computers and Mathematics with Applications (2006)","DOI":"10.1016\/j.camwa.2006.07.013"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1023\/A:1007968115863","volume":"21","author":"C.H. Ribeiro","year":"1998","unstructured":"Ribeiro, C.H.: Embedding a Priori Knowledge in Reinforcement Learning. Journal of Intelligent and Robotic Systems\u00a021, 51\u201371 (1998)","journal-title":"Journal of Intelligent and Robotic Systems"},{"key":"11_CR23","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1023\/A:1015008417172","volume":"17","author":"C. Ribeiro","year":"2002","unstructured":"Ribeiro, C.: Reinforcement Learning Agent. Artificial Intelligence Review\u00a017, 223\u2013250 (2002)","journal-title":"Artificial Intelligence Review"},{"key":"11_CR24","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/3-540-49097-3_2","volume-title":"Computational Learning Theory","author":"R.S. Sutton","year":"1999","unstructured":"Sutton, R.S.: Open theoretical questions in reinforcement learning. In: Fischer, P., Simon, H.U. (eds.) EuroCOLT 1999. LNCS (LNAI), vol.\u00a01572, pp. 11\u201317. Springer, Heidelberg (1999)"},{"key":"11_CR25","volume-title":"Artificial Intelligence: A Modern Approach","author":"S.J. Russell","year":"2003","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education Inc., New Jersey (2003)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Shapiro, D., Langley, P., Shachter, R.: Using Background Knowledge to Speed Reinforcement Learning in Physical Agents. In: AGENTS 2001, Montr\u00e9al, Quebec, Canada (2001)","DOI":"10.1145\/375735.376305"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Shokri, M., Tizhoosh, H.R.: Using Reinforcement Learning for Image Thresholding. In: Canadian Conference on Electrical and Computer Engineering, vol.\u00a01, pp. 1231\u20131234 (2003)","DOI":"10.1109\/CCECE.2003.1226121"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Shokri, M., Tizhoosh, H.R., Kamel, M.: Opposition-Based Q(\u03bb) Algorithm. In: International Joint Conference on Neural Networks, IJCNN, pp. 646\u2013653 (2006)","DOI":"10.1109\/IJCNN.2006.246689"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Shokri, M., Tizhoosh, H.R., Kamel, M.S.: Opposition-Based Q(\u03bb) with Non-Markovian Update. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Hawaii, USA (accepted, 2007)","DOI":"10.1109\/ADPRL.2007.368201"},{"key":"11_CR30","volume-title":"Reinforcement learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"11_CR31","unstructured":"Tizhoosh, H.R.: Reinforcement Learning Based on Actions and Opposite Actions. In: ICGST International Conference on Artificial Intelligence and Machine Learning (AIML 2005), Cairo, Egypt (2005)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Tizhoosh, H.R.: Opposition-Based Learning: A New Scheme for Machine Intelligence. In: International Conference on Computational Intelligence for Modeling Control and Automation - CIMCA 2005, Vienna, Austria, vol.\u00a0I, pp. 695\u2013701 (2005)","DOI":"10.1109\/CIMCA.2005.1631345"},{"issue":"4","key":"11_CR33","doi-asserted-by":"crossref","first-page":"578","DOI":"10.20965\/jaciii.2006.p0578","volume":"10","author":"H.R. Tizhoosh","year":"2006","unstructured":"Tizhoosh, H.R.: Opposition-Based Reinforcement learning. Journal of Advanced Computational Intelligence and Intelligent Informatics\u00a010(4), 578\u2013585 (2006)","journal-title":"Journal of Advanced Computational Intelligence and Intelligent Informatics"},{"key":"11_CR34","volume-title":"E-Learning Networked Environments and Architectures: A Knowledge Processing Perspective","author":"H.R. Tizhoosh","year":"2005","unstructured":"Tizhoosh, H.R., Shokri, M., Kamel, M.: The Outline of a Reinforcement-Learning Agents for E-Learning Applications. In: Pierre, S. (ed.) E-Learning Networked Environments and Architectures: A Knowledge Processing Perspective. Springer, Heidelberg (2005)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Ventresca, M., Tizhoosh, H.R.: Improving the Convergence of Backpropagation by Opposite Transfer Functions. In: IEEE Congress on Evolutionary Computation, IEEE World Congress on Computational Intelligence, Vancouver, July 16-21 (2006)","DOI":"10.1109\/IJCNN.2006.247153"},{"key":"11_CR36","volume-title":"Learning from Delayed Rewards","author":"C.J.C.H. Watkins","year":"1989","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. Cambridge University, Cambridge (1989)"},{"key":"11_CR37","first-page":"279","volume":"8","author":"C.J.H. Watkins","year":"1992","unstructured":"Watkins, C.J.H., Dayan, P.: Technical Note, Q-Learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Studies in Computational Intelligence","Oppositional Concepts in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-70829-2_11.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T17:03:22Z","timestamp":1709226202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-70829-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540708261","9783540708292"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-70829-2_11","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[]}}