{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T11:54:09Z","timestamp":1775476449070,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B1111500002"],"award-info":[{"award-number":["2020B1111500002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022048"],"award-info":[{"award-number":["62022048"]}],"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":["62276150"],"award-info":[{"award-number":["62276150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"THU-Bosch JCML"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tsmc.2023.3312411","type":"journal-article","created":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T18:08:12Z","timestamp":1699034892000},"page":"1014-1025","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2587-2660","authenticated-orcid":false,"given":"Qisen","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukun","family":"Tong","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Shi","sequence":"additional","affiliation":[{"name":"Autonomous Vehicle Delivery Department, Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-9283","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","article-title":"Solving Rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv:1910.07113"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870724"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3128193"},{"key":"ref6","article-title":"A survey on interpretable reinforcement learning","author":"Glanois","year":"2021","journal-title":"arXiv:2112.13112"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref9","article-title":"A survey on explainable reinforcement learning: Concepts, algorithms, challenges","author":"Qing","year":"2022","journal-title":"arXiv:2211.06665"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014561"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"ref12","first-page":"1787","article-title":"Visualizing and understanding Atari agents","volume-title":"Proc. ICML","volume":"80","author":"Greydanus"},{"key":"ref13","first-page":"1899","article-title":"Graying the black box: Understanding DQNs","volume-title":"Proc. ICML","volume":"48","author":"Zahavy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037898"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"issue":"11","key":"ref16","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13962"},{"key":"ref19","first-page":"138","article-title":"Learning embedded maps of Markov processes","volume-title":"Proc. ICML","author":"Engel"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00522"},{"key":"ref21","first-page":"1","article-title":"Multi-focus attention network for efficient deep reinforcement learning","volume-title":"Proc. Workshops 31st AAAI Conf. Artif. Intell.","author":"Choi"},{"key":"ref22","first-page":"12329","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume-title":"Proc. NeurIPS","author":"Mott"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3091885"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108927"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3096495"},{"key":"ref26","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. ICLR (Workshop Poster)","author":"Simonyan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref28","article-title":"Not just a black box: Learning important features through propagating activation differences","author":"Shrikumar","year":"2016","journal-title":"arXiv:1605.01713"},{"key":"ref29","article-title":"SmoothGrad: Removing noise by adding noise","author":"Smilkov","year":"2017","journal-title":"arXiv:1706.03825"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7244"},{"key":"ref32","first-page":"151","article-title":"RISE: Randomized input sampling for explanation of black-box models","volume-title":"Proc. BMVC","author":"Petsiuk"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref34","first-page":"1","article-title":"Explaining image classifiers by counterfactual generation","volume-title":"Proc. ICLR","author":"Chang"},{"key":"ref35","first-page":"1","article-title":"One-step pixel-level perturbation-based saliency detector","volume-title":"Proc. BMVC","author":"Kim"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482446"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.06.030"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2868372"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref40","first-page":"6967","article-title":"Real time image saliency for black box classifiers","volume-title":"Proc. NIPS","author":"Dabkowski"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133717"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17235"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"Pearl","year":"2009"},{"key":"ref44","article-title":"Causality for machine learning","author":"Sch\u00f6lkopf","year":"2019","journal-title":"arXiv:1911.10500"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20648"},{"key":"ref46","first-page":"1","article-title":"Human causal transfer: Challenges for deep reinforcement learning","volume-title":"Proc. CogSci","author":"Edmonds"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/bjps\/axi147"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"ref49","article-title":"Distal explanations for model-free explainable reinforcement learning","author":"Madumal","year":"2020","journal-title":"arXiv:2001.10284"},{"key":"ref50","first-page":"19622","article-title":"Learning tree interpretation from object representation for deep reinforcement learning","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref51","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref53","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref54","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3397269"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref57","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1512.02134"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref59","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref60","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. ICLR","author":"Kostrikov"},{"key":"ref61","first-page":"1","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. NeurIPS","author":"Kumar"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref63","volume-title":"Duckietown environments for OpenAI gym","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref64","article-title":"Explainability in reinforcement learning: Perspective and position","author":"Krajna","year":"2022","journal-title":"arXiv:2203.11547"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3544903.3544905"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.107052"},{"key":"ref67","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref68","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1177\/1473871620904671"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023394"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10403399\/10306329.pdf?arnumber=10306329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:26:04Z","timestamp":1705688764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10306329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":70,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2023.3312411","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}