{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:53:09Z","timestamp":1777654389714,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196619","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"4637-4643","source":"Crossref","is-referenced-by-count":34,"title":["Learning to combine primitive skills: A step towards versatile robotic manipulation \u00a7"],"prefix":"10.1109","author":[{"given":"Robin","family":"Strudel","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Pashevich","sequence":"additional","affiliation":[]},{"given":"Igor","family":"Kalevatykh","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Truncated horizon policy search: Combining reinforcement learning & imitation learning","author":"sun","year":"2018","journal-title":"ICLRE"},{"key":"ref38","article-title":"Fast policy learning through imitation and reinforcement","author":"cheng","year":"2018","journal-title":"UAI"},{"key":"ref33","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"NIPS"},{"key":"ref32","article-title":"Latent space policies for hierarchical reinforcement learning","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref31","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"ICLRE"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"AAAI"},{"key":"ref37","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"ICLR Workshop"},{"key":"ref36","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"ICLRE"},{"key":"ref35","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"NIPS"},{"key":"ref34","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"ICML"},{"key":"ref28","article-title":"Meta learning shared hierarchies","author":"frans","year":"2018","journal-title":"ICLRE"},{"key":"ref27","article-title":"Feudal Reinforcement Learning","author":"dayan","year":"1993","journal-title":"NIPS"},{"key":"ref29","article-title":"Composing complex skills by learning transition policies with proximity reward induction","author":"lee","year":"2019","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat6385"},{"key":"ref20","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"NIPS"},{"key":"ref22","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"NIPS"},{"key":"ref21","article-title":"Learning by playing - Solving sparse reward tasks from scratch","author":"riedmiller","year":"2018","journal-title":"MLR"},{"key":"ref24","article-title":"DART: Noise injection for robust imitation learning","author":"laskey","year":"2017","journal-title":"CoRL"},{"key":"ref23","article-title":"Learning dexterous manipulation policies from experience and imitation","author":"kumar","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ICLRE"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref53","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"NIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref11","article-title":"Neural modular control for embodied question answering","author":"das","year":"2018","journal-title":"CoRL"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep Q-Learning from demonstrations","author":"hester","year":"2018","journal-title":"AAAI"},{"key":"ref12","article-title":"Hierarchical imitation and reinforcement learning","author":"le","year":"2018","journal-title":"ICML"},{"key":"ref13","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967622"},{"key":"ref15","article-title":"Learning to combine primitive skills: A step towards versatile robotic manipulation, project website","year":"0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707053"},{"key":"ref17","article-title":"Deep reinforcement learning for robotic manipulation","author":"gu","year":"2016","journal-title":"ICML"},{"key":"ref18","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"JMLR"},{"key":"ref19","article-title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","author":"popov","year":"2017"},{"key":"ref4","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","author":"toussaint","year":"2015","journal-title":"IJCAI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943079"},{"key":"ref6","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"ross","year":"2014"},{"key":"ref5","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"NIPS"},{"key":"ref8","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref49","article-title":"ShapeNet: An information-rich 3D model repository","author":"chang","year":"2015"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref45","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref48","article-title":"PyBullet, Python module for physics simulation, robotics and machine learning","author":"courmans","year":"2016","journal-title":"Github"},{"key":"ref47","article-title":"Pytorch implementations of reinforcement learning algorithms","author":"kostrikov","year":"2018","journal-title":"Github"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"AAAI"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196619.pdf?arnumber=9196619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T14:02:08Z","timestamp":1668780128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196619","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}