{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:35:17Z","timestamp":1730255717140,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1109\/icra.2014.6907425","type":"proceedings-article","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T20:32:36Z","timestamp":1412109156000},"page":"3903-3909","source":"Crossref","is-referenced-by-count":3,"title":["A connectionist actor-critic algorithm for faster learning and biological plausibility"],"prefix":"10.1109","author":[{"given":"Leonard","family":"Johard","sequence":"first","affiliation":[]},{"given":"Emanuele","family":"Ruffaldi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/BF01415010"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref12","article-title":"Reducing network depth in the cascade-correlation learning architecture","author":"baluja","year":"1994","journal-title":"Tech Rep"},{"key":"ref13","article-title":"Experimental analysis of aspects of the cascade-correlation learning architecture","author":"squires","year":"0","journal-title":"Working Paper"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1523\/JNEUROSCI.1478-05.2005"},{"key":"ref15","first-page":"278","article-title":"An analysis of actor\/critic algorithms using eligibility traces: Reinforcement learning with imperfect value function","author":"kimura","year":"1998","journal-title":"Proceedings of the 15th International Conference on Machine Learning"},{"key":"ref16","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"1999","journal-title":"NIPS Citeseer"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/s00213-006-0578-x"},{"key":"ref4","article-title":"On-line q-learning using connectionist systems","author":"rummery","year":"1994","journal-title":"Tech Rep"},{"year":"1989","author":"watkins","article-title":"Learning from Delayed Rewards","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1287\/moor.12.3.441"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/BF00992696"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref7","first-page":"1361","article-title":"Signal-to-noise ratio analysis of policy gradient algorithms","author":"roberts","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/BF00115009"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.jmp.2008.12.005"},{"key":"ref9","first-page":"1105","article-title":"Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning","volume":"22","author":"legenstein","year":"2009","journal-title":"Advances in Neural Inform Process Syst"}],"event":{"name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2014,5,31]]},"location":"Hong Kong, China","end":{"date-parts":[[2014,6,7]]}},"container-title":["2014 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6895053\/6906581\/06907425.pdf?arnumber=6907425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T21:56:06Z","timestamp":1490306166000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6907425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icra.2014.6907425","relation":{},"subject":[],"published":{"date-parts":[[2014,5]]}}}