{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:35:04Z","timestamp":1768314904019,"version":"3.49.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001852","name":"Indo-French Centre for the Promotion of Advanced Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001852","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886011","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"1911-1916","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning with Quasi-Hyperbolic Discounting"],"prefix":"10.1109","author":[{"given":"S.R.","family":"Eshwar","sequence":"first","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayank","family":"Motwani","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Department of Computer Science and Engineering,Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nibedita","family":"Roy","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gugan","family":"Thoppe","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/h0076860"},{"key":"ref2","article-title":"Differential inclusions: Set-valued maps and viability theory, springer science & business media","author":"Aubin"},{"key":"ref3","article-title":"Reinforcement learning and optimal control","author":"Bertsekas","year":"2019","journal-title":"Athena Scientific"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2023.3288931"},{"key":"ref5","article-title":"Stochastic approximation: a dynamical systems view-point","volume":"48","author":"Borkar","year":"2009"},{"issue":"2","key":"ref6","first-page":"469","article-title":"Rates of time preference for saving lives","volume":"82","author":"Cropper","year":"1992","journal-title":"The American Economic Review"},{"key":"ref7","article-title":"The foundations of behavioral economic analysis","author":"Dhami","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1257\/002205102320161311"},{"key":"ref9","article-title":"Demystifying approximate value-based rl with \u03f5-greedy exploration: A differential inclusion view","author":"Gopalan","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.08.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-020-00443-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/003355397555253"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/2118482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/2296547"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/17442508.2016.1215450"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref17","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1765(81)90067-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1037"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886011.pdf?arnumber=10886011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T08:10:56Z","timestamp":1740643856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886011\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886011","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}