{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:38:03Z","timestamp":1762101483990,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6638519","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"4539-4543","source":"Crossref","is-referenced-by-count":7,"title":["Cooperative off-policy prediction of Markov decision processes in adaptive networks"],"prefix":"10.1109","author":[{"given":"Sergio Valcarcel","family":"Macua","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianshu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santiago","family":"Zazo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali H.","family":"Sayed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1002\/9780470374122"},{"key":"15","first-page":"1204","article-title":"Convergent temporal-difference learning with arbitrary smooth function approximation","volume":"22","author":"maei","year":"2009","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/s10955-011-0284-x"},{"key":"13","article-title":"Diffusion adaptation over networks","author":"sayed","year":"2012","journal-title":"E-Reference Signal Processing"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2033729"},{"key":"11","first-page":"1609","article-title":"A convergent o(n) temporal-difference algorithm for off-policy learning with linear function approximation","author":"sutton","year":"2009","journal-title":"Advances in Neural Information Processing Systems 21"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2198470"},{"key":"3","first-page":"299","article-title":"Multi-timescale nexting in a reinforcement learning robot","author":"modayil","year":"2012","journal-title":"From Animals to Animats 12 7426 of Lecture Notes in Computer Science"},{"key":"2","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume":"2","author":"sutton","year":"2011","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"10","first-page":"91","article-title":"GQ(lambda): A general gradient algorithm for temporal-difference prediction learning with eligibility traces","author":"maei","year":"2010","journal-title":"Proc Conf on Artificial General Intelli-gence"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5280-0"},{"key":"4","article-title":"Scaling-up knowledge for a cognizant robot","author":"degris","year":"2012","journal-title":"Notes of the AAAI Spring Symposium Series"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967355"},{"key":"8","first-page":"959","article-title":"Should one compute the temporal difference fix point or minimize the Bellman residual? the unified oblique projection view","author":"scherrer","year":"2010","journal-title":"Proc 7th Int Conf Machine Learning"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2013,5,26]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06638519.pdf?arnumber=6638519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:40:49Z","timestamp":1646952049000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6638519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6638519","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}