{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:12:47Z","timestamp":1787497967371,"version":"build-2736575974"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,1]]},"DOI":"10.1109\/ssci47803.2020.9308288","type":"proceedings-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T18:12:38Z","timestamp":1609870358000},"page":"250-257","source":"Crossref","is-referenced-by-count":4,"title":["A3DQN: Adaptive Anderson Acceleration for Deep Q-Networks"],"prefix":"10.1109","author":[{"given":"Melike","family":"Ermis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Insoon","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Globally convergent typeI Anderson acceleration for non-smooth fixed-point iterations","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1808 10393"},{"key":"ref11","first-page":"10231","article-title":"Regularized Anderson acceleration for off-policy deep reinforcement learning","author":"shi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Anderson accelerated Douglas-Rachford Splitting","author":"fu","year":"2019","journal-title":"arXiv preprint arXiv 1908 11444"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/10078356X"},{"key":"ref15","article-title":"Markov decision processes: discrete stochastic dynamic programming","author":"puterman","year":"2014","journal-title":"John Wiley & Sons"},{"key":"ref16","first-page":"2721","article-title":"Count-based exploration with neural density models","volume":"70","author":"ostrovski","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref4","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref8","article-title":"Anderson acceleration for reinforcement learning","author":"geist","year":"2018","journal-title":"arXiv preprint arXiv 1809 09501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/321296.321305"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref1","first-page":"3338","article-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning","author":"guo","year":"2014","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"712","article-title":"Regularized nonlinear acceleration","author":"scieur","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Canberra, ACT, Australia","start":{"date-parts":[[2020,12,1]]},"end":{"date-parts":[[2020,12,4]]}},"container-title":["2020 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9308061\/9308107\/09308288.pdf?arnumber=9308288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T12:31:41Z","timestamp":1670675501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9308288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/ssci47803.2020.9308288","relation":{},"subject":[],"published":{"date-parts":[[2020,12,1]]}}}