{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T10:38:10Z","timestamp":1780483090889,"version":"3.54.1"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.23919\/acc45564.2020.9147512","type":"proceedings-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T22:02:33Z","timestamp":1595887353000},"page":"4751-4756","source":"Crossref","is-referenced-by-count":1,"title":["Recent Advances in Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"M.","family":"Vidyasagar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1051027873"},{"key":"ref11","first-page":"2235","article-title":"Zap Q-learning","author":"devraj","year":"2017","journal-title":"31st Conference on Neural Information Processing Systems (NIPS 2017)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INDIANCC.2019.8715554"},{"key":"ref13","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref14","author":"vidyasagar","year":"2002","journal-title":"Learning and Generalization With Applications to Neural Networks and Control Systems"},{"key":"ref4","author":"sutton","year":"2018","journal-title":"Reinforcement learning An introduction Second edition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2907414"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2015.0733"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref7","author":"vidyasagar","year":"2014","journal-title":"Hidden Markov Processes Theory and Applications to Biology"},{"key":"ref2","author":"puterman","year":"2005","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"}],"event":{"name":"2020 American Control Conference (ACC)","location":"Denver, CO, USA","start":{"date-parts":[[2020,7,1]]},"end":{"date-parts":[[2020,7,3]]}},"container-title":["2020 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9140048\/9147203\/09147512.pdf?arnumber=9147512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,31]],"date-time":"2020-08-31T21:47:11Z","timestamp":1598910431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9147512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":14,"URL":"https:\/\/doi.org\/10.23919\/acc45564.2020.9147512","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}