{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:57:13Z","timestamp":1775109433968,"version":"3.50.1"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/devlrn.2012.6400849","type":"proceedings-article","created":{"date-parts":[[2013,1,7]],"date-time":"2013-01-07T21:36:02Z","timestamp":1357594562000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Reinforcement learning combined with human feedback in continuous state and action spaces"],"prefix":"10.1109","author":[{"family":"Ngo Anh Vien","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Ertel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"13","first-page":"66","article-title":"Fitted natural actor-critic: A new algorithm for continuous state-action MDPs","author":"melo","year":"0","journal-title":"Machine Learning and Knowledge Discovery in Databases European Conference ECML\/PKDD (2) 2008"},{"key":"11","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"3","first-page":"5","article-title":"Combining manual feedback with subsequent MDP reward signals for reinforcement learning","author":"knox","year":"0","journal-title":"9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2010"},{"key":"2","article-title":"Reinforcement learning from simultaneous human and MDP reward","author":"knox","year":"0","journal-title":"11st International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2012"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"7","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","article-title":"Neuronlike adaptive elements that can solve difficult learning control problems","volume":"13","author":"barto","year":"1983","journal-title":"IEEE Transactions on Systems Man & Cybernetics"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(77)90354-0"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Advances in Neural Information Processing Systems 12 [NIPS Conference Denver Colorado USA] 1999"}],"event":{"name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","location":"San Diego, CA, USA","start":{"date-parts":[[2012,11,7]]},"end":{"date-parts":[[2012,11,9]]}},"container-title":["2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6384412\/6400572\/06400849.pdf?arnumber=6400849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T05:18:33Z","timestamp":1498022313000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6400849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2012.6400849","relation":{},"subject":[],"published":{"date-parts":[[2012,11]]}}}