{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T19:51:29Z","timestamp":1768333889557,"version":"3.49.0"},"reference-count":46,"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\/cdc57313.2025.11312439","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"2713-2719","source":"Crossref","is-referenced-by-count":0,"title":["Iteration Complexity for Robust CMDP for finite policy space"],"prefix":"10.1109","author":[{"given":"Sourav","family":"Ganguly","sequence":"first","affiliation":[{"name":"NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA"}]},{"given":"Arnob","family":"Ghosh","sequence":"additional","affiliation":[{"name":"NJIT,Dept. of Electrical and Computer Engineering,Newark,NJ,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref2","article-title":"Exploration-exploitation in constrained mdps","author":"Efroni","year":"2020"},{"key":"ref3","article-title":"Near-optimal sample complexity bounds for constrained mdps","author":"Vaswani","year":"2022"},{"key":"ref4","article-title":"Natural policy gradient primal-dual method for constrained markov decision processes","author":"Ding","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","first-page":"3304","article-title":"Provably efficient safe exploration via primal-dual policy optimization","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ding"},{"key":"ref6","first-page":"3274","article-title":"Triple-q: A model-free algorithm for constrained reinforcement learning with sublinear regret and zero constraint violation","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Wei"},{"key":"ref7","first-page":"13303","article-title":"Provably efficient model-free constrained rl with linear function approximation","volume":"35","author":"Ghosh","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","article-title":"Rectified robust policy optimization for model-uncertain constrained reinforcement learning without strong duality","author":"Ma","year":"2025"},{"key":"ref11","article-title":"Near-optimal policy identification in robust constrained markov decision processes via epigraph form","author":"Kitamura","year":"2024"},{"key":"ref12","article-title":"Distributionally robust constrained reinforcement learning under strong duality","author":"Zhang","year":"2024"},{"issue":"178","key":"ref13","first-page":"1","article-title":"Optimistic online mirror descent for bridging stochastic and adversarial online convex optimization","volume":"25","author":"Chen","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile","author":"Mertikopoulos","year":"2018"},{"key":"ref15","article-title":"Last-iterate convergent policy gradient primal-dual methods for constrained mdps","author":"Ding","year":"2023"},{"key":"ref16","first-page":"1054","article-title":"Towards achieving sub-linear regret and hard constraint violation in model-free rl","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ghosh"},{"key":"ref17","first-page":"11480","article-title":"Crpo: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref18","first-page":"1047","article-title":"Dope: Doubly optimistic and pessimistic exploration for safe reinforcement learning","volume":"35","author":"Bura","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"An efficient pessimistic-optimistic algorithm for stochastic linear bandits with general constraints","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref21","article-title":"Robustness in markov decision problems with uncertain transition matrices","volume":"16","author":"Nilim","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"The curious price of distributional robustness in reinforcement learning with a generative model","volume":"36","author":"Shi","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"32211","article-title":"Robust reinforcement learning using offline data","volume":"35","author":"Panaganti","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"9728","article-title":"Improved sample complexity bounds for distributionally robust reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Xu"},{"key":"ref26","first-page":"6995","article-title":"Sample-optimal parametric q-learning using linearly additive features","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref27","first-page":"23484","article-title":"Policy gradient method for robust reinforcement learning","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref28","first-page":"35763","article-title":"Policy gradient in robust mdps with global convergence guarantee","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref29","first-page":"3331","article-title":"Finite-sample regret bound for distributionally robust offline tabular reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Zhou"},{"key":"ref30","article-title":"Robust constrained-mdps: Soft-constrained robust policy optimization under model uncertainty","author":"Russel","year":"2020"},{"key":"ref31","article-title":"Robust constrained reinforcement learning for continuous control with model misspecification","author":"Mankowitz","year":"2020"},{"key":"ref32","article-title":"Robust constrained reinforcement learning","author":"Wang","year":"2022"},{"key":"ref33","first-page":"9582","article-title":"Sample complexity of robust reinforcement learning with a generative model","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Panaganti"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2225"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref36","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"International Conference on Machine Learning","author":"Le"},{"key":"ref38","article-title":"Reinforcement learning with convex constraints","volume":"32","author":"Miryoosefi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref40","article-title":"Fast convergence of regularized learning in games","volume":"28","author":"Syrgkanis","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","first-page":"26772","article-title":"No-regret learning in time-varying zero-sum games","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref42","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume":"33","author":"Daskalakis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Decentralized optimistic hyperpolicy mirror descent: Provably no-regret learning in markov games","author":"Zhan","year":"2022"},{"key":"ref44","article-title":"Iteration complexity for robust cmdp","author":"Ganguly","year":"2024"},{"key":"ref45","article-title":"Efficient policy optimization in robust constrained mdps with iteration complexity guarantees","author":"Ganguly","year":"2025"},{"key":"ref46","article-title":"Faster last-iterate convergence of policy optimization in zero-sum markov games","author":"Cen","year":"2022"}],"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\/11312439.pdf?arnumber=11312439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:14:02Z","timestamp":1768292042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312439","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}