{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:31:13Z","timestamp":1729650673416,"version":"3.28.0"},"reference-count":8,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010640","type":"proceedings-article","created":{"date-parts":[[2015,1,20]],"date-time":"2015-01-20T02:48:03Z","timestamp":1421722083000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Using supervised training signals of observable state dynamics to speed-up and improve reinforcement learning"],"prefix":"10.1109","author":[{"given":"Daniel L","family":"Elliott","sequence":"first","affiliation":[]},{"given":"Charles","family":"Anderson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"1128","article-title":"On discovery and learning of models with predictive representations of state for agents with continuous actions and observations","author":"wingate","year":"2007","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref3","article-title":"Model-based reinforcement learning with continuous states and actions","author":"deisenroth","year":"2008","journal-title":"European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning (ESANN)"},{"key":"ref6","article-title":"Comparative evaluation of reinforcement learning with scalar rewards and linear regression with multidimensional feedback","author":"kormushev","year":"2013","journal-title":"ECML\/PKDD 2013 Workshop on Reinforcement Learning from Generalized Feedback Beyond Numeric Rewards"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"journal-title":"Geometric Data Analysis","year":"2001","author":"kirby","key":"ref8"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1109\/TNNLS.2013.2271454","article-title":"Goal representation heuristic dynamic programming on maze navigation","volume":"24","author":"ni","year":"2013","journal-title":"IEEE Trans Neural Networks and Learning Systems"},{"article-title":"Learning and problem solving with multilayer connectionist systems","year":"1986","author":"anderson","key":"ref2"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","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\/07010640.pdf?arnumber=7010640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T03:55:02Z","timestamp":1498190102000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010640","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}