{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T09:28:14Z","timestamp":1790846894066,"version":"4.1.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447501","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6120-6124","source":"Crossref","is-referenced-by-count":6,"title":["A Robust Quantile Huber Loss with Interpretable Parameter Adjustment in Distributional Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Parvin","family":"Malekzadeh","sequence":"first","affiliation":[{"name":"University of Toronto,The Edward S. Rogers Sr. Department of Electrical and Computer Engineering,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantinos N.","family":"Plataniotis","sequence":"additional","affiliation":[{"name":"University of Toronto,The Edward S. Rogers Sr. Department of Electrical and Computer Engineering,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zissis","family":"Poulos","sequence":"additional","affiliation":[{"name":"University of Toronto,Joseph L. Rotman School of Management,Toronto,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Toronto,Joseph L. Rotman School of Management,Toronto,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.076"},{"key":"ref2","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref4","article-title":"Robust reinforcement learning with distributional risk-averse formulation","author":"Clavier","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1129370"},{"key":"ref7","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on machine learning","author":"Dabney"},{"key":"ref8","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00362-021-01227-2"},{"key":"ref11","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Advances in neural information processing systems","volume":"32","author":"Yang"},{"key":"ref12","article-title":"Generalized huber loss for robust learning and its efficient minimization for a robust statistics","author":"Gokcesu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/21-EJS1957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/qj.4206"},{"key":"ref15","article-title":"Deep huber quantile regression networks","author":"Tyralis","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213503"},{"key":"ref17","first-page":"678","article-title":"Robust forward algorithms via pac-bayes and laplace distributions","volume-title":"Artificial Intelligence and Statistics","author":"Noy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793505"},{"key":"ref20","first-page":"7927","article-title":"Gmac: A distributional perspective on actor-critic framework","volume-title":"International Conference on Machine Learning","author":"Nam"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5626\/jok.2023.50.2.172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747886"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal transport: old and new","volume":"338","author":"Villani","year":"2009"},{"key":"ref24","article-title":"On the 1-wasserstein distance between location-scale distributions and the effect of differential privacy","author":"Chhachhi","year":"2023"},{"key":"ref25","first-page":"84","article-title":"Managing smile risk","volume":"September","author":"Hagan","year":"2002","journal-title":"Wilmott Magazine"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447501.pdf?arnumber=10447501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:44:02Z","timestamp":1722577442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447501","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}