{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:25:47Z","timestamp":1762953947981,"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\/iros55552.2023.10341451","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1697-1704","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Imitation Learning for Stochastic Environments"],"prefix":"10.1109","author":[{"given":"Maximilian","family":"Igl","sequence":"first","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Punit","family":"Shah","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Mougin","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sirish","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarun","family":"Gupta","sequence":"additional","affiliation":[{"name":"U. of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brandyn","family":"White","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyriacos","family":"Shiarlis","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[{"name":"Waymo Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Concrete problems in ai safety","author":"Amodei","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Fu","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-021-03141-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/460685a"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811990"},{"key":"ref10","first-page":"1802","article-title":"Learning policy representations in multiagent systems","volume-title":"International conference on machine learning","author":"Grover"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2999536"},{"key":"ref12","article-title":"Robust imitation of diverse behaviors","volume-title":"NeurIPS","author":"Wang","year":"2017"},{"key":"ref13","article-title":"Are gans created equal? a large-scale study","volume-title":"NeurIPS","author":"Lucic","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref16","article-title":"Generative adversarial imitation learning","volume-title":"NeurIPS","author":"Ho","year":"2016"},{"key":"ref17","article-title":"Model-based adversarial imitation learning","author":"Baram","year":"2016","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Bits: Bi-level imitation for traffic simulation","author":"Xu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref21","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","year":"2014"},{"key":"ref22","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref23","article-title":"Causal confusion in imitation learning","volume-title":"NeurIPS","author":"De Haan","year":"2019"},{"key":"ref24","article-title":"Trust region policy optimization","volume-title":"ICML","author":"Schulman","year":"2015"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref28","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"ICML","author":"Vezhnevets","year":"2017"},{"key":"ref29","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","volume-title":"ICLR","author":"Nachum","year":"2019"},{"key":"ref30","article-title":"Multitask soft option learning","volume-title":"UCA","author":"Igl","year":"2020"},{"key":"ref31","first-page":"418","article-title":"Ddco: Discovery of deep continuous options for robot learning from demonstrations","volume-title":"Conference on robot learning","author":"Krishnan"},{"key":"ref32","article-title":"Hierarchical imitation and reinforcement learning","author":"Le","year":"2018","journal-title":"ICML"},{"key":"ref33","article-title":"Taco: Learning task decomposition via temporal alignment for control","volume-title":"ICML","author":"Shiarlis","year":"2018"},{"key":"ref34","article-title":"Learning human behaviors from motion capture by adversarial imitation","author":"Merel","year":"2017","journal-title":"arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/405"},{"key":"ref36","article-title":"Imitation learning from visual data with multiple intentions","volume-title":"ICLR","author":"Tamar","year":"2018"},{"key":"ref37","article-title":"What-if motion prediction for autonomous driving","author":"Khandelwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Goal-conditioned imitation learning","volume-title":"NeurIPS","author":"Ding","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"Li","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","volume-title":"NeurIPS","author":"Hausman","year":"2017"},{"key":"ref43","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"ICLR","author":"Eysenbach","year":"2019"},{"key":"ref44","article-title":"Self-supervised exploration via disagreement","volume-title":"ICML","author":"Pathak","year":"2019"}],"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\/10341451.pdf?arnumber=10341451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:23:16Z","timestamp":1703031796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341451","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}