{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:35:58Z","timestamp":1768322158161,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312431","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"6063-6068","source":"Crossref","is-referenced-by-count":1,"title":["Convergence of regularized agent-state-based Q-learning in POMDPs"],"prefix":"10.1109","author":[{"given":"Amit","family":"Sinha","sequence":"first","affiliation":[{"name":"McGill University,Department of Electrical and Computer Engineering,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aditya","family":"Mahajan","sequence":"additional","affiliation":[{"name":"McGill University,Department of Electrical and Computer Engineering,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"issue":"12","key":"ref3","first-page":"1","article-title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","volume":"23","author":"Subramanian","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","first-page":"141","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume":"45","author":"Hausknecht","year":"2015","journal-title":"AAAI Fall Symposia"},{"key":"ref5","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPs","volume-title":"Int. Conf. Mach. Learn","author":"Igl"},{"key":"ref6","article-title":"On improving deep reinforcement learning for POMDPs","author":"Zhu","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636140"},{"issue":"255","key":"ref8","first-page":"1","article-title":"Simple agent, complex environment: Efficient reinforcement learning with agent states","volume":"23","author":"Dong","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC56724.2024.10886046"},{"key":"ref10","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"7","author":"Jaakkola","year":"1994"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1331"},{"key":"ref12","article-title":"Periodic agent-state based Q-learning for POMDPs","author":"Sinha","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref13","article-title":"Q-learning for stochastic control under general information structures and non-markovian environments","author":"Kera","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2024.105751"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. Conf. Mach. Learn","author":"Haarnoja"},{"key":"ref18","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Int. Conf. Mach. Learn","author":"Ahmed"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Int. Conf. Mach. Learn","author":"Schulman"},{"key":"ref22","article-title":"A unified view of entropy-regularized Markov decision processes","author":"Neu","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","article-title":"A theory of regularized Markov decision processes","volume-title":"Int. Conf. Mach. Learn","author":"Geist"},{"key":"ref24","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Int. Conf. Mach. Learn","author":"Hafner"},{"key":"ref25","first-page":"7444","article-title":"Solar: Deep structured representations for model-based reinforcement learning","volume-title":"Int. Conf. Mach. Learn","author":"Zhang"},{"key":"ref26","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Int. Conf. Learn. Represent","author":"Hafner"},{"key":"ref27","article-title":"Bridging state and history representations: Understanding self-predictive RL","volume-title":"Int. Conf. Learn. Represent","author":"Ni"},{"key":"ref28","article-title":"Entropy-regularized point-based value iteration","author":"Delecki","year":"2024"},{"key":"ref29","article-title":"DESPOT: Online POMDP planning with regularization","author":"Somani","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3250159"},{"key":"ref31","article-title":"The limits of pure exploration in POMDPs: When the observation entropy is enough","author":"Zamboni","year":"2024","journal-title":"Reinforcement Learning Journal"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02431-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56468-0"},{"key":"ref34","first-page":"3462","article-title":"Differentiable dynamic programming for structured prediction and attention","volume-title":"Int. Conf. Mach. Learn","author":"Mensch"},{"key":"ref35","article-title":"Sequential decomposition of sequential dynamic teams: applications to real-time communication and networked control systems","volume-title":"Ph.D. dissertation","author":"Mahajan","year":"2008"},{"key":"ref36","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Int. Conf. Mach. Learn","author":"Haarnoja"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022689125041"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312431","article-title":"Convergence of regularized agent-state-based q-learning in pomdps","author":"Sinha","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312431.pdf?arnumber=11312431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:14:09Z","timestamp":1768292049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312431","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}