{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:16:59Z","timestamp":1725625019828},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967358","type":"proceedings-article","created":{"date-parts":[[2011,8,3]],"date-time":"2011-08-03T21:40:00Z","timestamp":1312407600000},"page":"84-90","source":"Crossref","is-referenced-by-count":2,"title":["Agent self-assessment: Determining policy quality without execution"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Hans","sequence":"first","affiliation":[]},{"given":"Siegmund","family":"Duell","sequence":"additional","affiliation":[]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4634160"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04274-4_8"},{"journal-title":"Proc of the 19th European Conference on Artificial Intelligence","article-title":"Uncertainty propagation for efficient exploration in reinforcement learning","year":"0","key":"ref12"},{"key":"ref13","article-title":"Reducing policy degradation in neurodynamic programming","author":"gabel","year":"0","journal-title":"Proc of the European Symposium on Artificial Neural Networks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967368"},{"article-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref15"},{"article-title":"Bayesian Reasoning in Data Analysis: A Critical Introduction","year":"2003","author":"d\u2019 agostini","key":"ref16"},{"key":"ref17","article-title":"The wet game of chicken","author":"tresp","year":"1994","journal-title":"Siemens AG CT IC 4 Technical Report"},{"key":"ref18","article-title":"Model based Bayesian explo-ration","author":"dearden","year":"0","journal-title":"Proc of the Conf on Uncertainty in Artificial Intelligence"},{"key":"ref4","article-title":"Least-squares policy iteration","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2007.4371212"},{"key":"ref6","article-title":"Neural fitted Q-iteration - first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"0","journal-title":"16th European Conference on Machine Learning"},{"key":"ref5","article-title":"Tree-based batch mode reinforcement learning","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368182"},{"key":"ref7","article-title":"Neural rewards regression for near-optimal policy identification in Markovian and partial observable environments","author":"schneegass","year":"0","journal-title":"Proc of the European Symposium on Artificial Neural Networks"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S1469026801000172"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","article-title":"Batch reinforcement learning in a complex domain","author":"kalyanakrishnan","year":"0","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","start":{"date-parts":[[2011,4,11]]},"location":"Paris, France","end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967358.pdf?arnumber=5967358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T04:58:20Z","timestamp":1490072300000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967358","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}