{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:28:46Z","timestamp":1759332526914,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF)","doi-asserted-by":"publisher","award":["NRF-2019R1A2C1003713"],"award-info":[{"award-number":["NRF-2019R1A2C1003713"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,20]]},"DOI":"10.1109\/ictc52510.2021.9620901","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:49:57Z","timestamp":1638910197000},"page":"167-171","source":"Crossref","is-referenced-by-count":4,"title":["Reward Shaping to Learn Natural Object Manipulation With an Anthropomorphic Robotic Hand and Hand Pose Priors via On-Policy Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Patricio","family":"Rivera","sequence":"first","affiliation":[]},{"given":"Jiheon","family":"Oh","sequence":"additional","affiliation":[]},{"given":"Edwin","family":"Valarezo","sequence":"additional","affiliation":[]},{"given":"Gahyeon","family":"Ryu","sequence":"additional","affiliation":[]},{"given":"Hwanseok","family":"Jung","sequence":"additional","affiliation":[]},{"given":"Jin Hyunk","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jin Gyun","family":"Jeong","sequence":"additional","affiliation":[]},{"given":"Tae-Seong","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800110"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref14","first-page":"1","author":"vecerik","year":"2017","journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards"},{"key":"ref15","article-title":"A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations","author":"iyengar","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Learning Actionable Representations with Goal-Conditioned Policies","author":"ghosh","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref4","first-page":"390","article-title":"End-to-end differentiable adversarial imitation learning","author":"baram","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2810544"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref5","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref1","article-title":"Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review","author":"du","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_22"},{"journal-title":"Leap Motion","year":"2021","key":"ref21"}],"event":{"name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2021,10,20]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2021,10,22]]}},"container-title":["2021 International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9620727\/9620211\/09620901.pdf?arnumber=9620901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:42Z","timestamp":1652201622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9620901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,20]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ictc52510.2021.9620901","relation":{},"subject":[],"published":{"date-parts":[[2021,10,20]]}}}