{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:48:28Z","timestamp":1730270908838,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341403","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1675-1682","source":"Crossref","is-referenced-by-count":0,"title":["Imitation-Guided Multimodal Policy Generation from Behaviourally Diverse Demonstrations"],"prefix":"10.1109","author":[{"given":"Shibei","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rituraj","family":"Kaushik","sequence":"additional","affiliation":[{"name":"Aalto University,Department of Electrical Engineering and Automation,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Kaski","sequence":"additional","affiliation":[{"name":"Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ville","family":"Kyrki","sequence":"additional","affiliation":[{"name":"Aalto University,Department of Electrical Engineering and Automation,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14125-6_4"},{"key":"ref2","first-page":"897","article-title":"Appren-ticeship learning about multiple intentions","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Babes"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00151"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.11.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3177294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref8","article-title":"Intrinsically motivated re-inforcement learning","volume":"17","author":"Chentanez","year":"2004","journal-title":"Advances in neural information processing systems"},{"article-title":"Parameter space noise for exploration","volume-title":"International Conference on Learning Represen-tations","author":"Plappert","key":"ref9"},{"key":"ref10","article-title":"Learning from demonstration","volume":"9","author":"Schaal","year":"1996","journal-title":"Advances in neural infor-mation processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref12","first-page":"1259","article-title":"A divergence mini-mization perspective on imitation learning methods","volume-title":"Conference on Robot Learning","author":"Ghasemipour"},{"key":"ref13","first-page":"12805","article-title":"f-gail: Learning f-divergence for generative adversarial imitation learning","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"6036","article-title":"Provably efficient imitation learning from observation alone","volume-title":"International conference on machine learning","author":"Sun"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref16","first-page":"1","article-title":"A note on the evaluation of generative models","volume-title":"International Conference on Learning Representations (ICLR 2016)","author":"Theis","year":"2016"},{"key":"ref17","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Learning robust rewards with adverse-rial inverse reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Fu","year":"2018"},{"key":"ref19","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Veegan: Reducing mode collapse in gans using implicit variational learning","volume":"30","author":"Srivastava","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref23","first-page":"1755","article-title":"Imitating latent policies from observation","volume-title":"International conference on machine learning","author":"Edwards"},{"key":"ref24","first-page":"1426","article-title":"Generalization guarantees for imitation learning","volume-title":"Conference on Robot Learning","author":"Ren"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2021.1959397"},{"key":"ref26","article-title":"Latent policies for adversarial imitation learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"2229","article-title":"Adversarial imitation learning from state-only demonstrations","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","author":"Torabi"},{"article-title":"State alignment-based imitation learning","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref28"},{"key":"ref29","first-page":"22955","article-title":"Behavior transformers: Cloning k modes with one stone","volume":"35","author":"Shafiullah","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"447","article-title":"Exploration from demonstration for interactive reinforcement learning","volume-title":"Proceedings of the 2016 international conference on autonomous agents & multi-agent systems","author":"Subramanian"},{"key":"ref31","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"article-title":"Making efficient use of demonstrations to solve hard explo-ration problems","volume-title":"International Conference on Learning Represen-tations","author":"Gulcehre","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref36","first-page":"729","article-title":"Guided reinforcement learning with learned skills","volume-title":"Conference on Robot Learning","author":"Pertsch"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2704781"},{"key":"ref40","article-title":"Illuminating search spaces by mapping elites","author":"Mouret","year":"2015","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2735550"},{"volume-title":"Probabilistic machine learning: Advanced topics","year":"2022","author":"Murphy","key":"ref42"},{"journal-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2016","author":"Coumans","key":"ref43"},{"journal-title":"An environment for autonomous driving decision-making","year":"2018","author":"Leurent","key":"ref44"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341403.pdf?arnumber=10341403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:14:08Z","timestamp":1703031248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341403","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}