{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:04:34Z","timestamp":1779807874357,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,8]]},"DOI":"10.1145\/3801489.3806884","type":"proceedings-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:22:48Z","timestamp":1779805368000},"page":"213-215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1972-8582","authenticated-orcid":false,"given":"Phalguni","family":"Nanda","sequence":"first","affiliation":[{"name":"Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9915-5595","authenticated-orcid":false,"given":"Zaiwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Industrial Engineering, Purdue University, West Lafayette, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2022.0097"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.0249"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"R. Douc E. Moulines P. Priouret and P. Soulier. 2018. Markov Chains. Springer International Publishing. https:\/\/books.google.com\/books?id=QaZ-DwAAQBAJ","DOI":"10.1007\/978-3-319-97704-1"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3718-3726","author":"Haque Shaan Ul","year":"2025","unstructured":"Shaan Ul Haque and Siva Theja Maguluri. 2025. Stochastic approximation with unbounded Markovian noise: A general-purpose theorem. In International Conference on Artificial Intelligence and Statistics. PMLR, 3718-3726."},{"key":"e_1_3_2_1_6_1","volume-title":"Is Q-learning provably efficient? Advances in neural information processing systems","author":"Jin Chi","year":"2018","unstructured":"Chi Jin, Zeyuan Allen-Zhu, Sebastien Bubeck, and Michael I Jordan. 2018. Is Q-learning provably efficient? Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Linear Q-learning does not diverge in L: Convergence rates to a bounded set. Preprint arXiv:2501.19254","author":"Liu Xinyu","year":"2025","unstructured":"Xinyu Liu, Zixuan Xie, and Shangtong Zhang. 2025. Linear Q-learning does not diverge in L: Convergence rates to a bounded set. Preprint arXiv:2501.19254 (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"Human-level control through deep reinforcement learning. nature","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. nature, Vol. 518, 7540 (2015), 529-533."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3805624"},{"key":"e_1_3_2_1_10_1","volume-title":"Conference on Learning Theory. PMLR, 3185-3205","author":"Qu Guannan","year":"2020","unstructured":"Guannan Qu and Adam Wierman. 2020. Finite-time analysis of asynchronous stochastic approximation and Q-learning. In Conference on Learning Theory. PMLR, 3185-3205."},{"key":"e_1_3_2_1_11_1","volume-title":"A stochastic approximation method. The Annals of Mathematical Statistics","author":"Robbins Herbert","year":"1951","unstructured":"Herbert Robbins and Sutton Monro. 1951. A stochastic approximation method. The Annals of Mathematical Statistics (1951), 400-407."},{"key":"e_1_3_2_1_12_1","volume-title":"Machine learning","author":"Watkins Christopher JCH","year":"1992","unstructured":"Christopher JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning, Vol. 8, 3-4 (1992), 279-292."}],"event":{"name":"SIGMETRICS '26: ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","location":"Ann Arbor MI USA","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"]},"container-title":["Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:26:56Z","timestamp":1779805616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801489.3806884"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":12,"alternative-id":["10.1145\/3801489.3806884","10.1145\/3801489"],"URL":"https:\/\/doi.org\/10.1145\/3801489.3806884","relation":{},"subject":[],"published":{"date-parts":[[2026,6,8]]},"assertion":[{"value":"2026-06-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}