{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:17:41Z","timestamp":1787012261869,"version":"build-2736575974"},"reference-count":35,"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\/icra40945.2020.9196958","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"1149-1155","source":"Crossref","is-referenced-by-count":39,"title":["Efficient Bimanual Manipulation Using Learned Task Schemas"],"prefix":"10.1109","author":[{"given":"Rohan","family":"Chitnis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubham","family":"Tulsiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurabh","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","article-title":"SURREAL: Open-source reinforcement learning framework and robot manipulation benchmark","author":"fan","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref30","article-title":"Stable baselines","author":"hill","year":"2018"},{"key":"ref35","article-title":"Pyrobot: An open-source robotics framework for research and benchmarking","author":"murali","year":"2019"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10226","article-title":"Reinforcement learning with parameterized actions","author":"masson","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref11","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2016"},{"key":"ref12","article-title":"Hierarchical approaches for reinforcement learning in parameterized action space","author":"wei","year":"2018","journal-title":"The 2018 AAAI Spring Symposium Series"},{"key":"ref13","first-page":"166","article-title":"Modular multitask reinforcement learning with policy sketches","author":"andreas","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1142\/WSSRIS"},{"key":"ref15","article-title":"On the role of simulation in the study of autonomous mobile robots","author":"gat","year":"1995","journal-title":"AAAI Spring Symposium on Lessons Learned from Implemented Software Architectures for Physical Agents"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00117447"},{"key":"ref22","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Reasoning about probabilistic actions at multiple levels of granularity","author":"chrisman","year":"1994","journal-title":"AAAI Spring Sympos Decision-Theoretic Planning"},{"key":"ref24","article-title":"Meta learning shared hierarchies","author":"frans","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref23","first-page":"220","article-title":"Hierarchical solution of Markov decision processes using macro-actions","author":"hauskrecht","year":"1998","journal-title":"Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref25","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"}],"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\/09196958.pdf?arnumber=9196958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T08:59:15Z","timestamp":1668761955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196958","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}