{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:29:02Z","timestamp":1730230142325,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682832","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"3042-3046","source":"Crossref","is-referenced-by-count":0,"title":["Non-local Self-attention Structure for Function Approximation in Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhixiang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangwu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhendong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutao","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Computer Science"},{"article-title":"Torcs: The open racing car simulator","year":"2015","author":"wymann","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref13","article-title":"cGANs with projection discriminator","author":"miyato","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref15","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref16","article-title":"Self-attention generative adversarial networks","volume":"abs 1805 8318","author":"zhang","year":"2018","journal-title":"CoRR"},{"key":"ref17","article-title":"Non-local neural networks","author":"wang","year":"2018","journal-title":"CVPR"},{"key":"ref18","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","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":"2016","journal-title":"Nature"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proceedings of the 33nd International Conference on Machine Learning ICML 2016"},{"key":"ref5","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Computer Science"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"CoRR"},{"key":"ref9","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682832.pdf?arnumber=8682832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:23:04Z","timestamp":1657855384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682832","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}