{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:57:05Z","timestamp":1774454225765,"version":"3.50.1"},"reference-count":14,"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.2019.8682983","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"3057-3061","source":"Crossref","is-referenced-by-count":19,"title":["Reinforcement Learning with Safe Exploration for Network Security"],"prefix":"10.1109","author":[{"given":"Canhuang","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyue","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Provably robust learning-based approach for high-accuracy tracking control of lagrangian systems","author":"helwa","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref12","first-page":"2087","article-title":"Two-dimensional anti-jamming communication based on deep reinforcement learning","author":"han","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","first-page":"1","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"4312","article-title":"Safe exploration in finite markov decision processes with gaussian processes","author":"turchetta","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"1041","article-title":"Transfer learning in real-time strategy games using hybrid CBR\/RL","author":"sharma","year":"2007","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref5","first-page":"2147","article-title":"Transfer reinforcement learning with shared dynamics","author":"laroche","year":"2017","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref8","article-title":"Measuring and avoiding side effects using relative reachability","author":"krakovna","year":"2018","journal-title":"arXiv preprint arXiv 1806 01186"},{"key":"ref7","first-page":"1711","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"2012","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2549640"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CNS.2013.6682689"},{"key":"ref9","article-title":"Safe reinforcement learning via formal methods","author":"fulton","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"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\/08682983.pdf?arnumber=8682983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:05Z","timestamp":1657855025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682983","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}