{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:02:36Z","timestamp":1752278556981,"version":"3.41.2"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["61941113"],"award-info":[{"award-number":["61941113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology on Information System Engineering Laboratory","award":["05202004"],"award-info":[{"award-number":["05202004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tbdata.2024.3489415","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T13:36:45Z","timestamp":1730381805000},"page":"1787-1798","source":"Crossref","is-referenced-by-count":0,"title":["Reward Shaping Based on Optimal-Policy-Free"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7537-6844","authenticated-orcid":false,"given":"Jianghui","family":"Sang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-067X","authenticated-orcid":false,"given":"Yongli","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-2109","authenticated-orcid":false,"given":"Zaki Ahmad","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Worcester, Worcester, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5665-845X","authenticated-orcid":false,"given":"Xiaoliang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110335"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3150793"},{"key":"ref4","first-page":"5829","article-title":"Exploration-guided reward shaping for reinforcement learning under sparse rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Devidze"},{"key":"ref5","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref6","first-page":"12895","article-title":"Reward propagation using graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Klissarov"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109746"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119481"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2023.3262408"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3006084"},{"article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","year":"2019","author":"Jaques","key":"ref14"},{"article-title":"Offline policy evaluation across representations with applications to educational games","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Mandel","key":"ref15"},{"key":"ref16","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic Q-ensemble","volume-title":"Proc. Conf. Robot Learn.","author":"Lee"},{"article-title":"Offline reinforcement learning with implicit Q-learning","year":"2021","author":"Kostrikov","key":"ref17"},{"key":"ref18","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref19","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref20","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Ziebart"},{"key":"ref21","first-page":"17907","article-title":"Digraph inception convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tong"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1090\/cbms\/092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3240721"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3291358"},{"volume-title":"Experiments MATLAB","year":"2011","author":"Moler","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.89.052804"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref28"},{"key":"ref29","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.306"},{"key":"ref32","first-page":"433","article-title":"Dynamic potential-based reward shaping","volume-title":"Proc. 11th Int. Conf. Auton. Agents Multiagent Syst.","author":"Devlin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17337"},{"key":"ref35","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9292-6"},{"key":"ref37","first-page":"3504","article-title":"Potential based reward shaping for hierarchical reinforcement learning","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Gao"},{"key":"ref38","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","volume-title":"Proc. 10th Int. Conf. Auton. Agents Multiagent Syst.","author":"Devlin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525911002998"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00071"},{"key":"ref41","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403063"},{"key":"ref43","first-page":"6316","article-title":"Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121533"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref49","first-page":"4649","article-title":"On learning intrinsic rewards for policy gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"article-title":"Pruning convolutional neural networks for resource efficient inference","year":"2016","author":"Molchanov","key":"ref50"},{"key":"ref51","first-page":"14556","article-title":"Scalable graph neural networks via bidirectional propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov","key":"ref52"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11077791\/10740180.pdf?arnumber=10740180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T17:45:44Z","timestamp":1752255944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2024.3489415","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"type":"electronic","value":"2332-7790"},{"type":"electronic","value":"2372-2096"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}