{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T16:31:09Z","timestamp":1784046669115,"version":"3.55.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT (MSIT) of Korea Government, Development of Artificial Intelligence Technology that Continuously Improves Itself as the Situation Changes in the Real World","doi-asserted-by":"publisher","award":["2020-0-00440"],"award-info":[{"award-number":["2020-0-00440"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3085142","type":"journal-article","created":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T20:05:19Z","timestamp":1622491519000},"page":"93152-93164","source":"Crossref","is-referenced-by-count":9,"title":["Enhanced Off-Policy Reinforcement Learning With Focused Experience Replay"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-1998","authenticated-orcid":false,"given":"Seung-Hyun","family":"Kong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9515-7059","authenticated-orcid":false,"given":"I. Made Aswin","family":"Nahrendra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0008-3726","authenticated-orcid":false,"given":"Dong-Hee","family":"Paek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref32","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref31","first-page":"1","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","volume":"31","author":"hong","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"key":"ref36","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent"},{"key":"ref35","article-title":"Hyp-RL: Hyperparameter optimization by reinforcement learning","author":"jomaa","year":"2019","journal-title":"arXiv 1906 11527"},{"key":"ref34","first-page":"1","article-title":"DeepTraffic: Crowdsourced hyperparameter tuning of deep reinforcement learning systems for multi-agent dense traffic navigation","author":"fridman","year":"2018","journal-title":"Proc Neural Inf Process Syst (NIPS) Deep Reinforcement Learn Workshop"},{"key":"ref10","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref11","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12597-012-0077-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref17","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-016-0094-0"},{"key":"ref28","article-title":"A deeper look at experience replay","author":"zhang","year":"2017","journal-title":"arXiv 1712 01275"},{"key":"ref4","first-page":"1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"32","author":"hessel","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref27","first-page":"1","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"1","article-title":"Deep reinforcement learning with double Q-learning","volume":"30","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref6","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref1","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Proc NIPS DEEP Learn Workshop"},{"key":"ref20","first-page":"1","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"Proc ICML Workshop Reinforcement Learn Real Life"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"james","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-7758-7_1"},{"key":"ref23","first-page":"1","article-title":"Experience replay for continual learning","volume":"32","author":"rolnick","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref25","first-page":"3014","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","author":"mahmood","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09444458.pdf?arnumber=9444458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:40Z","timestamp":1639771060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9444458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3085142","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}