{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T22:10:03Z","timestamp":1756246203025,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968306","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1056-1063","source":"Crossref","is-referenced-by-count":4,"title":["Robot Learning via Human Adversarial Games"],"prefix":"10.1109","author":[{"given":"Jiali","family":"Duan","sequence":"first","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,USA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,USA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lerrel","family":"Pinto","sequence":"additional","affiliation":[{"name":"Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.-C.","family":"Jay Kuo","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,USA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanos","family":"Nikolaidis","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Computer Science,Los Angeles,USA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref32","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref31","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"301","article-title":"Algorithmic game theory","author":"lavi","year":"2007","journal-title":"Computationally-efficient approximate mechanisms"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.314.7080.572"},{"key":"ref35","volume":"103","author":"kutner","year":"2005","journal-title":"Applied Linear Statistical Models"},{"key":"ref34","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1075\/is.9.3.04bar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696468"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1075\/is.17.3.02nom"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref14","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref16","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","author":"knox","year":"2010","journal-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems Volume 1-Volume 1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref19","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2007.4813847"},{"key":"ref4","article-title":"Interactive learning from policy-dependent human feedback","author":"macglashan","year":"2017","journal-title":"arXiv preprint arXiv 1701 06190"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487342"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989190"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2008.4755944"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11485","article-title":"Deep tamer: Interactive agent shaping in high-dimensional state spaces","author":"warnell","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref8","article-title":"Explore, exploit or listen: Combining human feedback and policy model to speed up deep reinforcement learning in 3d worlds","author":"lin","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref7","first-page":"475","article-title":"Reinforcement learning from simultaneous human and mdp reward","author":"knox","year":"2012","journal-title":"Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref22","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"arumugam","year":"2019","journal-title":"arXiv preprint arXiv 1902 05023"},{"key":"ref24","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"arXiv preprint arXiv 1412 6572"},{"key":"ref23","article-title":"Adversarially learned inference","author":"dumoulin","year":"2016","journal-title":"arXiv preprint arXiv 1606 00704"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968306.pdf?arnumber=8968306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:30Z","timestamp":1756245270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968306","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}