{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:20:50Z","timestamp":1783225250165,"version":"3.54.6"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001695","name":"Japanese Science and Technology Agency (JST)","doi-asserted-by":"publisher","award":["JPMJER1603"],"award-info":[{"award-number":["JPMJER1603"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534243","type":"proceedings-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:32:37Z","timestamp":1632342757000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["Predictive PER: Balancing Priority and Diversity Towards Stable Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Sanghwa","family":"Lee","sequence":"first","affiliation":[{"name":"National Institute of Informatics, SOKENDAI,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaeyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Waterloo,Electrical & Computer Engineering,Waterloo,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ichiro","family":"Hasuo","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, SOKENDAI,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","author":"brittain","year":"2019","journal-title":"Prioritized sequence experience replay"},{"key":"ref32","article-title":"Distributed prioritized experience replay","author":"horgan","year":"0","journal-title":"ICLRE"},{"key":"ref31","first-page":"1001","article-title":"Generalized prioritized sweeping","author":"andre","year":"0","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref10","first-page":"1","article-title":"Experience selection in deep reinforcement learning for control","volume":"19","author":"de bruin","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","article-title":"Gaussian process behaviour in wide deep neural networks","author":"matthews","year":"0","journal-title":"ICLRE"},{"key":"ref12","author":"neal","year":"2018","journal-title":"A modern take on the bias-variance tradeoff in neural networks"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.1"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"ICLRE"},{"key":"ref15","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"0","journal-title":"ICLRE"},{"key":"ref16","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"NeurIPS"},{"key":"ref17","author":"zhao","year":"2019","journal-title":"Curiosity-driven experience prioritization via density estimation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"key":"ref19","author":"nair","year":"2015","journal-title":"Massively parallel methods for deep reinforcement learning"},{"key":"ref28","author":"vecer\u00edk","year":"2017","journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref3","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref6","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"ICML"},{"key":"ref29","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref5","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"ICLRE"},{"key":"ref8","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"0","journal-title":"AAAI"},{"key":"ref7","first-page":"3215","article-title":"Rainbow: combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"AAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","article-title":"Predictive PER: balancing priority and diversity towards stable deep reinforcement learning","author":"lee","year":"0","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref20","first-page":"3302","article-title":"Selective experience replay for lifelong learning","author":"isele","year":"0","journal-title":"AAAI"},{"key":"ref22","first-page":"2314","article-title":"A deeper look at planning as learning from replay","author":"van seijen","year":"0","journal-title":"ICML"},{"key":"ref21","article-title":"The importance of experience replay database composition in deep reinforcement learning","author":"de bruin","year":"0","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/666"},{"key":"ref23","author":"zhang","year":"2017","journal-title":"A deeper look at experience replay"},{"key":"ref26","first-page":"3223","article-title":"Deep Q-learning from demonstrations","author":"hester","year":"0","journal-title":"AAAI"},{"key":"ref25","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","author":"fedus","year":"0","journal-title":"ICML"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534243.pdf?arnumber=9534243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:23Z","timestamp":1659483143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534243","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}