{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:24:06Z","timestamp":1766269446917,"version":"3.28.0"},"reference-count":38,"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\/iros55552.2023.10342043","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"1200-1206","source":"Crossref","is-referenced-by-count":1,"title":["Learning from Pixels with Expert Observations"],"prefix":"10.1109","author":[{"given":"Minh-Huy","family":"Hoang","sequence":"first","affiliation":[{"name":"University of Science,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Dinh","sequence":"additional","affiliation":[{"name":"Hanoi University of Science & Technology,Hanoi,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Northeastern University,Boston,MA,USA,02115"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Policy learning in se (3) action spaces","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Hier-archical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/DEVLRN.2019.8850705"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICRA48506.2021.9561936"},{"key":"ref7","article-title":"Wish you were here: Hindsight goal selection for long-horizon dexterous manipulation","author":"Davchev","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/IROS47612.2022.9981295"},{"key":"ref9","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-3-031-21090-7_12"},{"key":"ref11","first-page":"2327","article-title":"Deep imitation learning for bimanual robotic manipulation","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforce-ment learning","author":"Gupta","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"International conference on machine learning","author":"Cohen"},{"key":"ref14","article-title":"Steerable cnns","author":"Cohen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Frame averaging for invariant and equivariant net-work design","author":"Puny","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"8614","article-title":"Spin-weighted spherical cnns","volume":"33","author":"Esteves","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"4199","article-title":"Mdp homomorphic networks: Group symmetries in reinforcement learning","volume":"33","author":"van der Pol","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"1713","article-title":"Equivariant q learning in spatial action spaces","volume-title":"Conference on Robot Learning","author":"Wang"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.15607\/RSS.2022.XVIII.071"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICRA46639.2022.9812146"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICRA40945.2020.9197468"},{"key":"ref22","first-page":"1401","article-title":"Learn2assemble with structured representations and search for robotic architectural construction","volume-title":"Conference on Robot Learning","author":"Funk"},{"key":"ref23","article-title":"Visual reinforcement learning with imagined goals","volume":"31","author":"Nair","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Planning with goal-conditioned policies","volume":"32","author":"Nasiriany","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Beyond pick-and-place: Tackling robotic stacking of diverse shapes","volume-title":"5th Annual Conference on Robot Learning","author":"Lee","year":"2021"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/IROS47612.2022.9981126"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.15607\/rss.2021.xvii.002"},{"key":"ref28","first-page":"335","article-title":"Bulletarrn: An open-source robotic manipulation benchmark and learning framework","volume-title":"The International Symposium of Robotics Research","author":"Wang"},{"key":"ref29","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning","author":"Schaul"},{"key":"ref30","article-title":"General e (2)-equivariant steerable cnns","volume":"32","author":"Weiler","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"So (2) equivariant reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2022"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref33","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Steerable cnns","author":"Cohen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Generalized out-of-distribution detection: A survey","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1007\/978-3-030-58580-8_30"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/CVPR42600.2020.00882"}],"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\/10342043.pdf?arnumber=10342043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:15:48Z","timestamp":1703031348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342043","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}