{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:08:13Z","timestamp":1768072093712,"version":"3.49.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906106"],"award-info":[{"award-number":["61906106"]}],"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":["61936009"],"award-info":[{"award-number":["61936009"]}],"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":["62022048"],"award-info":[{"award-number":["62022048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2018AAA0100701"],"award-info":[{"award-number":["2018AAA0100701"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2018YFB1702903"],"award-info":[{"award-number":["2018YFB1702903"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2020.3037898","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T21:54:31Z","timestamp":1605304471000},"page":"1-1","source":"Crossref","is-referenced-by-count":25,"title":["Self-Supervised Discovering of Interpretable Features for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Wenjie","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiji","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","first-page":"10 231","article-title":"Regularized anderson acceleration for off-policy deep reinforcement learning,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref4","article-title":"Learning to navigate in complex environments,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mirowski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884797"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00701"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2954501"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"ref13","first-page":"3145","article-title":"Learning important features through propagating activation differences,","author":"Shrikumar"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref15","first-page":"4765","article-title":"A unified approach to interpreting model predictions,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref18","first-page":"1899","article-title":"Graying the black box: Understanding DQNs,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zahavy"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014561"},{"key":"ref20","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref21","first-page":"1787","article-title":"Visualizing and understanding atari agents,","volume-title":"Proc. Int. Conf. Mach. Lear.","author":"Greydanus"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_25"},{"key":"ref23","first-page":"12 350","article-title":"Towards interpretable reinforcement learning using attention augmented agents,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mott"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6161"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref27","article-title":"Duckietown environments for OpenAI Gym,","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24873-3_4"},{"key":"ref29","first-page":"97","article-title":"Policy explanation in factored Markov decision processes,","volume-title":"Proc. 4th Eur. Workshop Probabilistic Graphical Models","author":"Elizalde"},{"key":"ref30","first-page":"303","article-title":"Improving robot controller transparency through autonomous policy explanation,","volume-title":"Proc. 12th ACM\/IEEE Int. Conf. Hum.-Robot Interact.","author":"Hayes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9613"},{"key":"ref32","first-page":"2494","article-title":"Verifiable reinforcement learning via policy extraction,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bastani"},{"key":"ref33","article-title":"Conservative Q-improvement: Reinforcement learning for an interpretable decision-tree policy,","author":"Roth","year":"2019"},{"key":"ref34","article-title":"Contrastive explanations for reinforcement learning in terms of expected consequences,","volume-title":"Proc. Workshop Explainable AI IJCAI","author":"Waa"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0841-3"},{"key":"ref37","first-page":"138","article-title":"Learning embedded maps of Markov processes,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engel"},{"key":"ref38","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref40","article-title":"SmoothGrad: Removing noise by adding noise,","author":"Smilkov","year":"2017"},{"key":"ref41","article-title":"Visualizing deep neural network decisions: Prediction difference analysis,","author":"Zintgraf","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref44","article-title":"RISE: Randomized input sampling for explanation of black-box models,","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Petsiuk"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref46","first-page":"272","article-title":"Explaining deep neural networks with a polynomial time algorithm for shapley values approximation,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ancona"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref48","first-page":"6967","article-title":"Real time image saliency for black box classifiers,","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dabkowski"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref50","article-title":"Deep attention recurrent Q-network,","author":"Sorokin","year":"2015"},{"key":"ref51","article-title":"Learning to predict where to look in interactive environments using deep recurrent Q-learning,","author":"Mousavi","year":"2016"},{"key":"ref52","article-title":"Learn to interpret atari agents,","author":"Yang","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00522"},{"key":"ref54","article-title":"Multi-focus attention network for efficient deep reinforcement learning,","volume-title":"Proc. Workshops 31st AAAI Conf. Artif. Intell.","author":"Choi"},{"key":"ref55","article-title":"Proximal policy optimization algorithms,","author":"Schulman","year":"2017"},{"key":"ref56","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":"ref57","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods,","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/475"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref60","article-title":"Continuous control with deep reinforcement learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","article-title":"Rethinking atrous convolution for semantic image segmentation,","author":"Chen","year":"2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref64","article-title":"OpenAI Gym,","author":"Brockman","year":"2016"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/S0952523808080899"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.156"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09259236.pdf?arnumber=9259236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:13:46Z","timestamp":1704842026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9259236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3037898","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}