{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:01:30Z","timestamp":1729630890509,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,6]]},"DOI":"10.1109\/ijcnn.2008.4634208","type":"proceedings-article","created":{"date-parts":[[2008,9,29]],"date-time":"2008-09-29T16:31:26Z","timestamp":1222705886000},"page":"2915-2921","source":"Crossref","is-referenced-by-count":2,"title":["Tradeoff between exploration and exploitation of OQ(λ) with non-Markovian update in dynamic environments"],"prefix":"10.1109","author":[{"given":"Maryam","family":"Shokri","sequence":"first","affiliation":[]},{"given":"Hamid R.","family":"Tizhoosh","sequence":"additional","affiliation":[]},{"given":"Mohamed S.","family":"Kamel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2006.1716100"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368201"},{"key":"18","first-page":"529","article-title":"difference learning applied to a high-performance game-playing program","author":"schaeffer","year":"2001","journal-title":"International Joint Conference on Artificial Intelligence"},{"journal-title":"Scaling Average-Reward Reinforcement Learning for Product Delivery","year":"2004","author":"proper","key":"15"},{"journal-title":"Artificial Intelligence A Modern Approach","year":"2003","author":"russell","key":"16"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"14","article-title":"inverted autonomous helicopter flight via reinforcement learning","author":"ng","year":"2004","journal-title":"International Symposium on Experimental Robotics"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"journal-title":"Active Sensing Using Reinforcement Learning IROS","year":"2004","author":"kwok","key":"12"},{"key":"21","article-title":"reinforcement learning for personalizing image search","author":"shokri","year":"2006","journal-title":"LORNET Annual E-Leaming Conference on Intelligent Interactive Learning Object Repositories"},{"journal-title":"A Reinforcement Agent for Threshold Fusion Journal of Applied Soft Computing ASOC-309","year":"2006","author":"shokri","key":"20"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/CCCRV.2004.1301490"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2003.1226121"},{"key":"24","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1613\/jair.859","article-title":"optimizing dialogue management with reinforcement learning: experiments with the nj-fun system","volume":"16","author":"singh","year":"2002","journal-title":"Journal of Artificial Intelligence Research (JAIR)"},{"key":"25","first-page":"537","article-title":"scaling reinforcement learning toward robocup soccer","author":"stone","year":"2001","journal-title":"Eighteenth International Conference on Machine Learning (ICML"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"26"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/CIMCA.2005.1631345"},{"key":"28","article-title":"reinforcement learning based on actions and opposite actions","author":"tizhoosh","year":"2005","journal-title":"ICGST International Conference on Artificial Intelligence and Machine Learning (AIML-05)"},{"key":"29","doi-asserted-by":"crossref","first-page":"578","DOI":"10.20965\/jaciii.2006.p0578","article-title":"opposition-based reinforcement learning","volume":"10","author":"tizhoosh","year":"2006","journal-title":"Journal of Advanced Computational Intelligence and Intelligent Informatics"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2004.1398413"},{"key":"10","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"reinforcement learning: a survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1016912"},{"key":"30","article-title":"the outline of a reinforcement-learning agents for e-learning applications","author":"tizhoosh","year":"0","journal-title":"E-learning networked environments and architectures A knowledge processing perspective"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74024-7_6"},{"key":"6","article-title":"improving elevator performance using reinforcement learning","volume":"8","author":"crites","year":"1996","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"5"},{"key":"31","volume":"17","author":"yan","year":"2005","journal-title":"Solitaire Man Versus Machine Advances in Neural Information Processing Systems"},{"key":"4","first-page":"24","article-title":"knightcap: a chess program that learns by combining td() with game-tree search","author":"baxter","year":"1998","journal-title":"Machine Learning Proceedings of the Fifteenth International Conference (ICML"},{"key":"9","first-page":"1393","article-title":"cobot: a social reinforcement. learning agent","author":"isbell","year":"2002","journal-title":"Proceedings of Neural Information Processing Systems 14 (NIPS)"},{"year":"0","key":"8"}],"event":{"name":"2008 IEEE International Joint Conference on Neural Networks (IJCNN 2008 - Hong Kong)","start":{"date-parts":[[2008,6,1]]},"location":"Hong Kong, China","end":{"date-parts":[[2008,6,8]]}},"container-title":["2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4625775\/4633757\/04634208.pdf?arnumber=4634208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T05:02:58Z","timestamp":1557810178000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4634208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2008.4634208","relation":{},"subject":[],"published":{"date-parts":[[2008,6]]}}}