{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T01:26:43Z","timestamp":1775698003311,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/allerton.2018.8636075","type":"proceedings-article","created":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T03:04:31Z","timestamp":1551409471000},"page":"478-485","source":"Crossref","is-referenced-by-count":74,"title":["The Effects of Memory Replay in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ruishan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/2897824.2925881","article-title":"Terrain-adaptive locomotion skills using deep reinforcement learning","volume":"35","author":"peng","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref11","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"7587","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref14","first-page":"528","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2008","journal-title":"Twenty-Fourth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref15","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"tessler","year":"2016","journal-title":"arXiv preprint arXiv 1604 07255"},{"key":"ref16","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref17","author":"van seijen","year":"2013","journal-title":"Efficient planning in mdps by small backups"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"key":"ref4","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329241"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref7","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":"ref2","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref1","volume":"48","author":"borkar","year":"2009","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/105971239300100403"}],"event":{"name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2018,10,2]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8630872\/8635635\/08636075.pdf?arnumber=8636075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:10:45Z","timestamp":1598227845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8636075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/allerton.2018.8636075","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}