{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T19:18:42Z","timestamp":1788290322846,"version":"build-2803163510"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"NASA ARMD University Leadership Initiative","award":["80NSSC24M0070"],"award-info":[{"award-number":["80NSSC24M0070"]}]},{"name":"National Science Foundation","award":["2300355"],"award-info":[{"award-number":["2300355"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tac.2026.3678838","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:10:13Z","timestamp":1774901413000},"page":"6155-6162","source":"Crossref","is-referenced-by-count":0,"title":["Finite Time Convergence Analysis of Policy Gradient Learning in Stochastic Stackelberg Games"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2175-3402","authenticated-orcid":false,"given":"Pranoy","family":"Das","sequence":"first","affiliation":[{"name":"Purdue University","place":["West Lafayette, IN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7624-7737","authenticated-orcid":false,"given":"Muhammad Aneeq uz","family":"Zaman","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign","place":["Champaign, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7060-3956","authenticated-orcid":false,"given":"Vijay","family":"Gupta","sequence":"additional","affiliation":[{"name":"Purdue University","place":["West Lafayette, IN, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref2","first-page":"1478","article-title":"Computing Stackelberg equilibria in discounted stochastic games (corrected version)","volume-title":"Proc. 26th Conf. Artif. Intell.","author":"Vorobeychik","year":"2012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20908"},{"key":"ref5","first-page":"11213","article-title":"Oracles & followers: Stackelberg equilibria in deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gerstgrasser","year":"2023"},{"issue":"35","key":"ref6","first-page":"1","article-title":"Can reinforcement learning find Stackelberg-Nash equilibria in general-sum Markov games with myopically rational followers?","volume":"24","author":"Han","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0847"},{"key":"ref8","article-title":"Unrolled generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Metz","year":"2017"},{"key":"ref9","first-page":"7953","article-title":"A game theoretic framework for model based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rajeswaran","year":"2020"},{"key":"ref10","first-page":"3133","article-title":"Implicit learning dynamics in Stackelberg games: Equilibria characterization, convergence analysis, and empirical study","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fiez","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3330797"},{"key":"ref12","article-title":"Convergent first-order methods for bi-level optimization and Stackelberg games","author":"Maheshwari","year":"2023"},{"key":"ref13","article-title":"Stackelberg policy gradient: Evaluating the performance of leaders and followers","volume-title":"Proc. ICLR Workshop Gamification Multiagent Solutions","author":"Vu","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644265"},{"key":"ref15","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Daskalakis","year":"2020"},{"key":"ref16","article-title":"Global convergence of multi-agent policy gradient in Markov potential games","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Leonardos","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2023.0065"},{"key":"ref18","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2017"},{"key":"ref19","article-title":"Soft actorcritic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref20","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahmed","year":"2019"},{"key":"ref21","first-page":"5916","article-title":"Revisiting the Softmax Bellman operator: New benefits and new perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2019"},{"key":"ref22","article-title":"Equivalence between policy gradients and soft Q-learning","author":"Schulman","year":"2017"},{"key":"ref23","volume-title":"Dynamic Noncooperative Game Theory","author":"Baar","year":"1998"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52119-6_20"},{"key":"ref25","article-title":"Follower agnostic methods for Stackelberg games","author":"Maheshwari","year":"2023"},{"issue":"1","key":"ref26","first-page":"4431","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","first-page":"309","article-title":"Fast planning in stochastic games","volume-title":"Proc. 16th Conf. Uncertainty Artif. Intell.","author":"Kearns","year":"2000"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2008.56"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0014"},{"key":"ref30","first-page":"6820","article-title":"On the global convergence rates of Softmax policy gradient methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mei","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/20M1387341"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2024.3358284"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2024.3387208"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2025.3540965"},{"key":"ref35","first-page":"2160","article-title":"A theory of regularized Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Geist","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"key":"ref37","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Asadi","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.2151"},{"key":"ref39","first-page":"10178","article-title":"Oracle-free reinforcement learning in mean-field games along a single sample path","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zaman","year":"2023"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611974997","volume-title":"First-Order Methods in Optimization","author":"Beck","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16919"},{"key":"ref42","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum","year":"2017"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/11672239\/11457656-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11672239\/11457656.pdf?arnumber=11457656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T19:04:31Z","timestamp":1788289471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11457656\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tac.2026.3678838","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}