{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:41:59Z","timestamp":1730270519273,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341578","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"5504-5510","source":"Crossref","is-referenced-by-count":1,"title":["Deep Adversarial Reinforcement Learning for Object Disentangling"],"prefix":"10.1109","author":[{"given":"Melvin","family":"Laux","sequence":"first","affiliation":[{"name":"TU Darmstadt,Intelligent Autonomous Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oleg","family":"Arenz","sequence":"additional","affiliation":[{"name":"TU Darmstadt,Intelligent Autonomous Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"TU Darmstadt,Intelligent Autonomous Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joni","family":"Pajarinen","sequence":"additional","affiliation":[{"name":"TU Darmstadt,Intelligent Autonomous Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Stable baselines","year":"2018","author":"hill","key":"ref32"},{"article-title":"Openai baselines","year":"2017","author":"dhariwal","key":"ref31"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref30"},{"key":"ref10","article-title":"End to end learning for self-driving cars","volume":"abs 1604 7316","author":"bojarski","year":"2016","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9290-3"},{"key":"ref12","first-page":"173","author":"levine","year":"2016","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3006789"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"goodfellow","key":"ref15"},{"key":"ref16","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989190"},{"key":"ref28","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","volume":"abs 1703 5407","author":"sukhbaatar","year":"2017","journal-title":"CoRR"},{"article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","year":"2017","author":"silver","key":"ref4"},{"key":"ref27","article-title":"Paired open-ended trailblazer (POET): endlessly generating increasingly complex and diverse learning environments and their solutions","volume":"abs 1901 1753","author":"wang","year":"2019","journal-title":"CoRR"},{"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","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"The sl simulation and real-time control software package","year":"2009","author":"schaal","key":"ref29"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"berner","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"article-title":"Solving rubik’s cube with a robot hand","year":"2019","author":"akkaya","key":"ref7"},{"key":"ref2","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","article-title":"Soft actor-critic algorithms and applications","volume":"abs 1812 5905","author":"haarnoja","year":"2018"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref1"},{"key":"ref20","article-title":"Robust deep reinforcement learning with adversarial attacks","volume":"abs 1712 3632","author":"pattanaik","year":"2017","journal-title":"CoRR"},{"key":"ref22","first-page":"3932","article-title":"Adversari-ally robust policy learning: Active construction of physically-plausible perturbations","author":"mandlekar","year":"2017"},{"article-title":"Adversarial attacks on neural network policies","year":"2017","author":"huang","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref23","article-title":"Adversarial policies: Attacking deep reinforcement learning","volume":"abs 1905 10615","author":"gleave","year":"2019","journal-title":"CoRR"},{"key":"ref26","article-title":"Reverse curriculum generation for reinforcement learning","volume":"abs 1707 5300","author":"florensa","year":"2017","journal-title":"CoRR"},{"article-title":"Automatic goal generation for reinforcement learning agents","year":"2017","author":"held","key":"ref25"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341578.pdf?arnumber=9341578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:52:05Z","timestamp":1656453125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341578","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}