{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:45:03Z","timestamp":1730270703764,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981295","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"4765-4772","source":"Crossref","is-referenced-by-count":1,"title":["Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"David","family":"Klee","sequence":"first","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ondrej","family":"Biza","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Platt","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multi-goal reinforcement learning: Challenging robotics environ-ments and request for research","volume-title":"arXiv preprint","author":"Plappert","year":"2018"},{"key":"ref2","article-title":"Hierarchical planning in the now","volume-title":"Workshops at the Twenty-Fourth AAAI Conference on Artifi-cial Intelligence","author":"Kaelbling","year":"2010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref4","article-title":"Temporal difference models: Model-free deep rl for model-based control","author":"Pong","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"113","article-title":"Energy-based hindsight experience prioriti-zation","volume-title":"2nd Annual Conference on Robot Learning, CoRL 2018, Zurich, Switzerland, 29\u201331 October 2018, Proceedings","author":"Zhao"},{"key":"ref7","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA","author":"Zhao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197468"},{"key":"ref9","first-page":"1401","article-title":"Learn2assemble with structured representations and search for robotic architectural construction","volume-title":"Conference on Robot Learning","author":"Funk"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143518"},{"key":"ref11","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3\u20138, 2018","author":"Nair"},{"key":"ref12","article-title":"Planning with goal-conditioned policies","author":"Nasiriany","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Reasoning about physical interactions with object-oriented prediction and planning","author":"Janner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"1514","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","author":"Florensa","year":"2018"},{"key":"ref15","article-title":"Automatic curriculum learning through value disagreement","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Pro-cessing Systems"},{"key":"ref16","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume-title":"1st Annual Conference on Robot Learning, CoRL 2017","author":"Florensa","year":"2017"},{"key":"ref17","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Sukhbaatar","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989109"},{"key":"ref21","first-page":"4682","article-title":"Learning portable representations for high-level planning","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event","volume":"119","author":"James"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_16"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref24","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5575"},{"key":"ref26","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Watter","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"journal-title":"Pybullet, a python module for physics simulation in robotics, games and machine learning","year":"2017","author":"Coumans","key":"ref30"},{"key":"ref31","article-title":"Policy learning in se (3) action spaces","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.035"},{"key":"ref33","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","author":"Zeng","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref35","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning","author":"Schaul"},{"key":"ref36","first-page":"3675","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":"ref37","first-page":"1713","article-title":"Equivariant q learning in spatial action spaces","volume-title":"Conference on Robot Learning","author":"Wang"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981295.pdf?arnumber=9981295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:44:33Z","timestamp":1706759073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981295","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}