{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:23:50Z","timestamp":1730262230840,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"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":[[2021,10,13]]},"DOI":"10.1109\/iecon48115.2021.9589967","type":"proceedings-article","created":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T23:47:51Z","timestamp":1636588071000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Inferring Cost Functions Using Reward Parameter Search and Policy Gradient Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Emir","family":"Arditi","sequence":"first","affiliation":[]},{"given":"Tjasa","family":"Kunavar","sequence":"additional","affiliation":[]},{"given":"Emre","family":"Ugur","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Babic","sequence":"additional","affiliation":[]},{"given":"Erhan","family":"Oztop","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-017-9702-7"},{"key":"ref11","article-title":"Continuous inverse optimal control with locally optimal examples","author":"levine","year":"2012","journal-title":"ICML ’12 Proceedings of the 29th International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2013-13470"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"32 868 ep","DOI":"10.1038\/srep32868","article-title":"Human motor adaptation in whole body motion","volume":"6","author":"babic","year":"2016","journal-title":"Scientific Reports"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2019.07.030"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref6","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref5","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref8","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref7","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"ICML"},{"key":"ref2","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"ICML"},{"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"},{"article-title":"Maximum entropy deep inverse reinforcement learning","year":"2015","author":"wulfmeier","key":"ref9"}],"event":{"name":"IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society","start":{"date-parts":[[2021,10,13]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,10,16]]}},"container-title":["IECON 2021 \u2013 47th Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9588332\/9589036\/09589967.pdf?arnumber=9589967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:50:05Z","timestamp":1652201405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9589967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/iecon48115.2021.9589967","relation":{},"subject":[],"published":{"date-parts":[[2021,10,13]]}}}