{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T08:01:15Z","timestamp":1772870475906,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/ijcnn.2017.7966389","type":"proceedings-article","created":{"date-parts":[[2017,7,10]],"date-time":"2017-07-10T21:41:30Z","timestamp":1499722890000},"page":"4214-4221","source":"Crossref","is-referenced-by-count":9,"title":["Batch reinforcement learning on the industrial benchmark: First experiences"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Hein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michel","family":"Tokic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Hentschel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas A.","family":"Runkler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkmar","family":"Sterzing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref12","author":"bakker","year":"2004","journal-title":"The state of mind Reinforcement learning with recurrent neural networks"},{"key":"ref13","author":"sch\u00e4fer","year":"2008","journal-title":"Reinforcement learning with recurrent neural networks"},{"key":"ref14","author":"depeweg","year":"2016","journal-title":"Learning and policy search in stochastic dynamical systems with bayesian neural networks"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368182"},{"key":"ref16","author":"hein","year":"2016","journal-title":"Introduction to the “Industrial Benchmark"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4018\/IJSIR.2016070102"},{"key":"ref18","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref19","first-page":"653","article-title":"Reducing policy degradation in neurodynamic programming","author":"gabel","year":"2006","journal-title":"Proceedings of the European Symposium on Artificial Neural Networks"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MHS.1995.494215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"ref6","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","first-page":"1107","article-title":"Least-squares policy iteration","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2005.1571637"},{"key":"ref7","first-page":"317","article-title":"Neural fitted Q iteration ? first experiences with a data efficient neural reinforcement learning method","volume":"3720","author":"riedmiller","year":"2005","journal-title":"Proceedings of the European Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref9","first-page":"301","article-title":"Neural rewards regression for near-optimal policy identification in markovian and partial observable environments","author":"schneegass","year":"2007","journal-title":"Proc European Symp Artificial Neural Networks"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"ref22","first-page":"279","article-title":"Rprop - a fast adaptive learning algorithm","author":"riedmiller","year":"1992","journal-title":"Proc of the Int Symposium on Computer and Information Science VII"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_38"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967358"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_23"},{"key":"ref26","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proceedings of the Fourth Connectionist Models Summer School"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967361"}],"event":{"name":"2017 International Joint Conference on Neural Networks (IJCNN)","location":"Anchorage, AK, USA","start":{"date-parts":[[2017,5,14]]},"end":{"date-parts":[[2017,5,19]]}},"container-title":["2017 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7958416\/7965814\/07966389.pdf?arnumber=7966389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,12,13]],"date-time":"2017-12-13T19:36:02Z","timestamp":1513193762000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7966389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2017.7966389","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}