{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:34:34Z","timestamp":1780850074405,"version":"3.54.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671266"],"award-info":[{"award-number":["61671266"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836004"],"award-info":[{"award-number":["61836004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua-Guoqiang Research Program","award":["2019GQG006"],"award-info":[{"award-number":["2019GQG006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tnnls.2021.3080521","type":"journal-article","created":{"date-parts":[[2021,6,11]],"date-time":"2021-06-11T19:33:10Z","timestamp":1623439990000},"page":"6458-6472","source":"Crossref","is-referenced-by-count":12,"title":["Orientation-Preserving Rewards\u2019 Balancing in Reinforcement Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5013-1880","authenticated-orcid":false,"given":"Jinsheng","family":"Ren","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3181-6881","authenticated-orcid":false,"given":"Shangqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4813-2494","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref5","article-title":"RUDDER: Return decomposition for delayed rewards","author":"Arjona-Medina","year":"2018","journal-title":"arXiv:1806.07857"},{"key":"ref6","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. ICML","volume":"99","author":"Ng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref8","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref11","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"Popov","year":"2017","journal-title":"arXiv:1704.03073"},{"key":"ref12","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. ICML","volume":"98","author":"Randl\u00f8v"},{"key":"ref13","first-page":"359","article-title":"Urban driving with multi-objective deep reinforcement learning","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Li"},{"key":"ref14","first-page":"85","article-title":"Modular multi-objective deep reinforcement learning with decision values","volume-title":"Proc. Federated Conf. Comput. Sci. Inf. Syst. (FedCSIS)","author":"Tajmajer"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21236\/ada454702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2166\/hydro.2013.169"},{"key":"ref20","volume-title":"Theory and application of reward shaping in reinforcement learning","author":"Laud","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525911002998"},{"key":"ref22","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. ICLR","author":"Jaderberg"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2008.4670492"},{"key":"ref24","first-page":"197","article-title":"Multi-criteria reinforcement learning","volume-title":"Proc. ICML","volume":"98","author":"G\u00e1bor"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref26","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Christiano"},{"key":"ref27","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"Brown","year":"2019","journal-title":"arXiv:1904.06387"},{"issue":"1","key":"ref28","first-page":"4945","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"ref31","first-page":"162","article-title":"Reinforcement learning with bounded risk","volume-title":"Proc. ICML","author":"Geibel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35101-3_53"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref34","article-title":"Meta-gradient reinforcement learning","author":"Xu","year":"2018","journal-title":"arXiv:1805.09801"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89378-3_37"},{"key":"ref38","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref39","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0616-58"},{"key":"ref41","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref42","first-page":"3682","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Kulkarni"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9931397\/09452798.pdf?arnumber=9452798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:54:27Z","timestamp":1705013667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9452798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":46,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3080521","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}