{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T16:23:50Z","timestamp":1783873430721,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tnnls.2022.3217189","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T17:11:47Z","timestamp":1667581907000},"page":"8954-8968","source":"Crossref","is-referenced-by-count":16,"title":["Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8379-9385","authenticated-orcid":false,"given":"Chenjia","family":"Bai","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9800-6344","authenticated-orcid":false,"given":"Zhoufan","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1654-4681","authenticated-orcid":false,"given":"Lingxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and the Department of Management Sciences, Northwestern University, Evanston, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0482-4296","authenticated-orcid":false,"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[{"name":"Vector Institute, University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6568-1335","authenticated-orcid":false,"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoran","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and the Department of Management Sciences, Northwestern University, Evanston, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","first-page":"1","article-title":"Dynamic bottleneck for robust self-supervised exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bai"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3107202"},{"key":"ref5","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","volume-title":"arXiv:2109.06668","author":"Yang","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3129160"},{"key":"ref7","first-page":"577","article-title":"Principled exploration via optimistic bootstrapping and backward induction","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Bai"},{"key":"ref8","first-page":"1","article-title":"Brax\u2014A differentiable physics engine for large scale rigid body simulation","volume-title":"Proc. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Freeman"},{"key":"ref9","article-title":"Attend2Pack: Bin packing through deep reinforcement learning with attention","volume-title":"arXiv:2107.04333","author":"Zhang","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref11","first-page":"466","article-title":"A survey on reproducibility by evaluating deep reinforcement learning algorithms on real-world robots","volume-title":"Proc. Conf. Robot Learn.","author":"Lynnerup"},{"key":"ref12","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","volume-title":"arXiv:2005.01643","author":"Levine","year":"2020"},{"key":"ref13","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref14","article-title":"Behavior regularized offline reinforcement learning","volume-title":"arXiv:1911.11361","author":"Wu","year":"2019"},{"key":"ref15","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref16","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"arXiv:2106.06860","author":"Fujimoto","year":"2021"},{"key":"ref17","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref18","article-title":"Conservative offline distributional reinforcement learning","volume-title":"arXiv:2107.06106","author":"Jason Ma","year":"2021"},{"key":"ref19","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"arXiv:2102.08363","author":"Yu","year":"2021"},{"key":"ref20","first-page":"1","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref21","first-page":"1","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bai"},{"key":"ref22","first-page":"11319","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Wu"},{"key":"ref23","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","volume-title":"arXiv:2004.07219","author":"Fu","year":"2020"},{"key":"ref24","first-page":"1","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Henaff"},{"key":"ref25","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref26","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney"},{"key":"ref27","first-page":"1","article-title":"Risk-averse Bayes-adaptive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rigter"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2021.3131149"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927531"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3093429"},{"key":"ref32","first-page":"15909","article-title":"Non-crossing quantile regression for distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou"},{"key":"ref33","first-page":"1","article-title":"Risk-averse offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Urp\u00ed"},{"key":"ref34","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2307\/1428011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1257\/jep.15.4.143"},{"key":"ref38","first-page":"6193","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00122574"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/253675"},{"key":"ref41","article-title":"Algorithms for CVaR optimization in MDPs","volume-title":"arXiv:1406.3339","author":"Chow","year":"2014"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4310\/SII.2009.v2.n3.a4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/476"},{"key":"ref46","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref47","first-page":"1","article-title":"Keep doing what worked: Behavioral modelling priors for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Siegel"},{"key":"ref48","first-page":"1","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref49","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","volume-title":"arXiv:2206.02829","author":"Yang","year":"2022"},{"key":"ref50","first-page":"1","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref51","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"issue":"1","key":"ref52","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","first-page":"1","article-title":"Conservative safety critics for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bharadhwaj"},{"key":"ref54","article-title":"DSAC: Distributional soft actor critic for risk-sensitive reinforcement learning","volume-title":"arXiv:2004.14547","author":"Ma","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3082568"},{"key":"ref56","article-title":"Worst cases policy gradients","volume-title":"arXiv:1911.03618","author":"Charlie Tang","year":"2019"},{"key":"ref57","first-page":"1","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref58","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":"ref59","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5870"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10589508\/09940310.pdf?arnumber=9940310","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:05:15Z","timestamp":1761588315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9940310\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":60,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3217189","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}