{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:37:50Z","timestamp":1785955070844,"version":"3.56.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.23919\/acc.2018.8431181","type":"proceedings-article","created":{"date-parts":[[2018,8,17]],"date-time":"2018-08-17T20:16:10Z","timestamp":1534536970000},"page":"240-245","source":"Crossref","is-referenced-by-count":35,"title":["A Policy Search Method For Temporal Logic Specified Reinforcement Learning Tasks"],"prefix":"10.23919","author":[{"given":"Xiao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Calin","family":"Belta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref12","author":"chebotar","year":"2016","journal-title":"Path integral guided policy search"},{"key":"ref13","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","author":"montgomery","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"2012","journal-title":"ICML"},{"key":"ref4","author":"levine","year":"2016","journal-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection"},{"key":"ref3","first-page":"6922","author":"levine","year":"2015","journal-title":"End-to-end training of deep visuomotor policies"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9519-z"},{"key":"ref5","first-page":"1","author":"amodei","year":"2016","journal-title":"Concrete problems in ai safety"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2015.2428471"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525158"},{"key":"ref2","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":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"}],"event":{"name":"2018 Annual American Control Conference (ACC)","location":"Milwaukee, WI","start":{"date-parts":[[2018,6,27]]},"end":{"date-parts":[[2018,6,29]]}},"container-title":["2018 Annual American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8410068\/8430677\/08431181.pdf?arnumber=8431181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:04:15Z","timestamp":1598245455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8431181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":14,"URL":"https:\/\/doi.org\/10.23919\/acc.2018.8431181","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}