{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T23:26:07Z","timestamp":1751671567059,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206608","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["True Online TD(\u03bb)-Replay An Efficient Model-free Planning with Full Replay"],"prefix":"10.1109","author":[{"given":"Abdulrahman","family":"Altahhan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2314","article-title":"A deeper look at planning as learning from replay","volume":"37","author":"vanseijen","year":"0"},{"key":"ref11","article-title":"A deeper look at experience replay","author":"zhang","year":"2017","journal-title":"eprint arXiv 1712 01275"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/BF00992699","article-title":"Self-improving reactive agents based on reinforcement learning, planning and teaching","volume":"8","author":"lin","year":"1992","journal-title":"Machine Learning"},{"key":"ref13","first-page":"1","article-title":"True online temporal-difference learning","volume":"17","author":"van seijen","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"Learning to predict independent of span","author":"van hasselt","year":"2015","journal-title":"CoRR"},{"key":"ref15","article-title":"An investigation of model-free planning","author":"guez","year":"2019","journal-title":"CoRR"},{"key":"ref16","article-title":"Treeqn and atreec: Differentiable tree planning for deep reinforcement learning","author":"farquhar","year":"2017","journal-title":"CoRR"},{"key":"ref17","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2012","journal-title":"eprint arXiv 1206 3285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186318"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2328495"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26561-2_1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966040"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref6"},{"journal-title":"Optimal Control Based on Reinforcement Learning","year":"2019","author":"bertsekas","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref7"},{"journal-title":"Learning Deep Architectures for AI","year":"2009","author":"yoshua","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489300"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"Deep reinforcement learning","author":"li","year":"2018","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"305","DOI":"10.3758\/s13420-012-0082-6","article-title":"Evaluating the td model of classical conditioning","volume":"40","author":"ludvig","year":"2012","journal-title":"Learning & Behavior"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1059712313511648"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206608.pdf?arnumber=9206608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:56:34Z","timestamp":1656453394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206608","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}