{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T13:14:28Z","timestamp":1771334068057,"version":"3.50.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3213503","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T19:39:08Z","timestamp":1665689948000},"page":"1-12","source":"Crossref","is-referenced-by-count":12,"title":["Robust Losses for Learning Value Functions"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2461-3103","authenticated-orcid":false,"given":"Andrew","family":"Patterson","sequence":"first","affiliation":[{"name":"Computing Science, University of Alberta, Edmonton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Liao","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics, University of Waterloo, Waterloo, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5356-2950","authenticated-orcid":false,"given":"Martha","family":"White","sequence":"additional","affiliation":[{"name":"Computing Science, University of Alberta, Edmonton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref3","article-title":"Reinforcement learning through gradient descent","author":"Baird","year":"1999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830617"},{"key":"ref5","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref6","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref8","first-page":"1458","article-title":"Learning from conditional distributions via dual embeddings","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Dai"},{"key":"ref9","first-page":"1125","article-title":"SBEED: Convergent reinforcement learning with nonlinear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref10","article-title":"OpenAI baselines","author":"Dhariwal","year":"2017","journal-title":"GitHub Repository"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4153\/CJM-1949-007-x"},{"key":"ref12","first-page":"15456","article-title":"A kernel loss for solving the bellman equation","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Feng"},{"key":"ref13","first-page":"3524","article-title":"Gradient temporal-difference learning with regularized corrections","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghiassian"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref16","first-page":"4962","article-title":"Evaluating the performance of reinforcement learning algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jordan"},{"key":"ref17","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref18","article-title":"Inf-convolution, sous-additivit\u00e9, convexit\u00e9 des fonctions num\u00e9riques","volume":"1970","author":"Moreau","year":"1970","journal-title":"J. Math\u00e9matiques Pures Appliqu\u00e9es"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref20","first-page":"1373","article-title":"Revisiting rainbow: Promoting more insightful and inclusive deep reinforcement learning research","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Obando-Ceron"},{"key":"ref21","first-page":"1","article-title":"A generalized projected bellman error for off-policy value estimation in reinforcement learning","volume":"23","author":"Patterson","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611973433","volume-title":"Lectures on Stochastic Programming: Modeling and Theory","author":"Shapiro","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref25","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref26","first-page":"1609","article-title":"A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Sutton"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref30","article-title":"Deep reinforcement learning and the deadly triad","author":"van Hasselt","year":"2018"},{"key":"ref31","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref32","first-page":"494","article-title":"Investigating practical linear temporal difference learning","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"White"},{"key":"ref33","first-page":"3742","article-title":"Unifying task specification in reinforcement learning","volume-title":"Proc. Int. Conf. on Mach. Learn.","author":"White"},{"key":"ref34","article-title":"MinAtar: An atari-inspired testbed for thorough and reproducible reinforcement learning experiments","author":"Young","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09918637.pdf?arnumber=9918637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:54:19Z","timestamp":1705960459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9918637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3213503","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":[[2022]]}}}