{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:45:38Z","timestamp":1729622738376,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,6]]},"DOI":"10.1109\/ijcnn.2008.4634160","type":"proceedings-article","created":{"date-parts":[[2008,9,29]],"date-time":"2008-09-29T20:31:26Z","timestamp":1222720286000},"page":"2588-2595","source":"Crossref","is-referenced-by-count":2,"title":["Uncertainty propagation for quality assurance in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Schneegass","sequence":"first","affiliation":[]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Martinetz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Information Theory Inference and Learning Algorithms","year":"2003","author":"mackay","key":"19"},{"journal-title":"Proc of the International Joint Conference on Neural Networks","year":"2007","author":"maximilian schaefer","key":"22"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0324-7_15"},{"journal-title":"Guide to the Expression of Uncertainty in Measurement","year":"1993","key":"18"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_12"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143932"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273525"},{"key":"13","first-page":"761","article-title":"bayesian q-iearning.","author":"dearden","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"14","first-page":"150","article-title":"model based bayesian exploration","author":"dearden","year":"1999","journal-title":"Proc Fifteenth Conf on Uncertainty in Artificial Intelligence"},{"key":"11","first-page":"457","article-title":"bayesian policy gradient algorithms","volume":"19","author":"ghavamzadeh","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273534"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/S0747-7171(08)80013-2"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"3"},{"key":"20","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.1142\/5262","author":"d'agostini","year":"2003","journal-title":"Bayesian Reasoning in Data Analysis A Critical Introduction"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"key":"10","first-page":"751","article-title":"gaussian processes in reinforcement learning","volume":"16","author":"edward rasmussen","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/11776420_42"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_41"},{"key":"5","article-title":"approximate planning in large pomdps via reusable trajectories","volume":"12","author":"kearns","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"4","first-page":"560","article-title":"error bounds for approximate policy iteration","author":"munos","year":"2003","journal-title":"Proc of the International Conference on Machine Learning"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"8","first-page":"154","article-title":"bayes meets bellman: the gaussian process approach to temporal difference learning","author":"engel","year":"2003","journal-title":"Proc of the International Conference on Machine Learning"}],"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\/04634160.pdf?arnumber=4634160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T12:09:36Z","timestamp":1497787776000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4634160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2008.4634160","relation":{},"subject":[],"published":{"date-parts":[[2008,6]]}}}