{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:10:51Z","timestamp":1780539051173,"version":"3.54.1"},"reference-count":16,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010649","type":"proceedings-article","created":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T21:48:03Z","timestamp":1421704083000},"page":"1-6","source":"Crossref","is-referenced-by-count":12,"title":["On-policy Q-learning for adaptive optimal control"],"prefix":"10.1109","author":[{"given":"Sumit Kumar","family":"Jha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubhendu","family":"Bhasin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.automatica.2012.09.019","article-title":"A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems","volume":"49","author":"bhasin","year":"2013","journal-title":"Automatica"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5399753"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","article-title":"Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics","volume":"48","author":"jiang","year":"2012","journal-title":"Automatica"},{"key":"ref13","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref14","author":"bertsekas","year":"1987","journal-title":"Dynamic Programming Deterministic and Stochastic Models"},{"key":"ref15","article-title":"Nonlinear and adaptive control design","author":"kokotovic","year":"1995","journal-title":"John Wiley and Sons"},{"key":"ref16","author":"slotine","year":"1991","journal-title":"Applied nonlinear control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref3","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1016\/j.automatica.2014.02.015","article-title":"Reinforcement q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics","volume":"50","author":"kiumarsi","year":"2014","journal-title":"Automatica"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2850","DOI":"10.1016\/j.automatica.2012.06.008","article-title":"Integral q-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems","volume":"48","author":"lee","year":"2012","journal-title":"Automatica"},{"key":"ref1","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Orlando, FL, USA","start":{"date-parts":[[2014,12,9]]},"end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010649.pdf?arnumber=7010649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T23:55:02Z","timestamp":1498175702000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010649","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}