{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:52:26Z","timestamp":1780512746732,"version":"3.54.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"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":[[2022,7,11]]},"DOI":"10.1109\/aim52237.2022.9863259","type":"proceedings-article","created":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T15:39:30Z","timestamp":1661441970000},"page":"1192-1198","source":"Crossref","is-referenced-by-count":8,"title":["Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty"],"prefix":"10.1109","author":[{"given":"Kun","family":"Dong","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongle","family":"Luo","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erkang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Plasma Physics, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3082947"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref15","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108693"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref3","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"0"},{"key":"ref6","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018"},{"key":"ref5","first-page":"767","article-title":"Surreal: Open-source reinforcement learning framework and robot manipulation benchmark","author":"fan","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref8","article-title":"Reward shaping via meta-learning","author":"zou","year":"2019"},{"key":"ref7","article-title":"Dynamical distance learning for unsupervised and semi-supervised skill discovery","author":"hartikainen","year":"2019"},{"key":"ref2","article-title":"Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards","author":"schoettler","year":"2019"},{"key":"ref9","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref1","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref20","article-title":"Reinforcement learning with perturbed rewards","author":"wang","year":"2018"},{"key":"ref22","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"}],"event":{"name":"2022 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","location":"Sapporo, Japan","start":{"date-parts":[[2022,7,11]]},"end":{"date-parts":[[2022,7,15]]}},"container-title":["2022 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics (AIM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9863218\/9863240\/09863259.pdf?arnumber=9863259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T17:02:12Z","timestamp":1664211732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9863259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/aim52237.2022.9863259","relation":{},"subject":[],"published":{"date-parts":[[2022,7,11]]}}}