{"list":"other","total":53,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1604.02199","title":"Distributionally Robust Stochastic Optimization with Wasserstein Distance","created":"2016-04-08","cited_by_count":185},{"id":"2005.12900","title":"Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model","created":"2020-05-26","cited_by_count":109},{"id":"2002.00260","title":"Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning","created":"2020-02-01","cited_by_count":96},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73},{"id":"2205.12944","title":"Learning in Mean Field Games: A Survey","created":"2022-05-25","cited_by_count":61},{"id":"1910.12802","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","created":"2019-10-28","cited_by_count":59},{"id":"1706.04711","title":"Reinforcement Learning under Model Mismatch","created":"2017-06-15","cited_by_count":52},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51},{"id":"2002.04131","title":"Mean-Field Controls with Q-learning for Cooperative MARL: Convergence and Complexity Analysis","created":"2020-02-10","cited_by_count":49},{"id":"1907.02633","title":"On the Convergence of Model Free Learning in Mean Field Games","created":"2019-07-04","cited_by_count":48},{"id":"2003.12151","title":"Q-Learning in Regularized Mean-field Games","created":"2020-03-24","cited_by_count":42},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38},{"id":"1912.07883","title":"Mean-field Markov decision processes with common noise and open-loop controls","created":"2019-12-17","cited_by_count":25},{"id":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24},{"id":"1911.07314","title":"Dynamic Programming Principles for Mean-Field Controls with Learning","created":"2019-11-17","cited_by_count":23},{"id":"2106.06231","title":"Numerical Methods for Mean Field Games and Mean Field Type Control","created":"2021-06-11","cited_by_count":22},{"id":"2303.06993","title":"Actor-Critic learning for mean-field control in continuous time","created":"2023-03-13","cited_by_count":22},{"id":"2306.16208","title":"Continuous-time q-learning for mean-field control problems","created":"2023-06-28","cited_by_count":22},{"id":"2305.19004","title":"Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets","created":"2023-05-30","cited_by_count":16},{"id":"2011.12946","title":"Exploratory LQG Mean Field Games with Entropy Regularization","created":"2020-11-25","cited_by_count":15},{"id":"2007.13103","title":"Distributionally Robust Markov Decision Processes and their Connection to Risk Measures","created":"2020-07-26","cited_by_count":14},{"id":"2407.04521","title":"Unified continuous-time q-learning for mean-field game and mean-field control problems","created":"2024-07-05","cited_by_count":13},{"id":"1604.04057","title":"Dynamic programming for optimal control of stochastic McKean-Vlasov dynamics","created":"2016-04-14","cited_by_count":12},{"id":"1706.10186","title":"Computational aspects of robust optimized certainty equivalents and option pricing","created":"2017-06-30","cited_by_count":7},{"id":"1907.08860","title":"McKean-Vlasov optimal control: the dynamic programming principle","created":"2019-07-20","cited_by_count":6},{"id":"2009.00578","title":"Linear-Quadratic Zero-Sum Mean-Field Type Games: Optimality Conditions and Policy Optimization","created":"2020-09-01","cited_by_count":6},{"id":"2604.27372","title":"Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations","created":"2026-04-30","cited_by_count":6},{"id":"1511.09273","title":"Discrete time McKean-Vlasov control problem: a dynamic programming approach","created":"2015-11-30","cited_by_count":4},{"id":"1701.00196","title":"Robust Mean Field Linear-Quadratic-Gaussian Games with Unknown $L^2$-Disturbance","created":"2017-01-01","cited_by_count":4},{"id":"1808.02962","title":"Optimal Solutions to Infinite-Player Stochastic Teams and Mean-Field Teams","created":"2018-08-08","cited_by_count":4},{"id":"1908.01122","title":"Social Optima in Robust Mean Field LQG Control: From Finite to Infinite Horizon","created":"2019-08-03","cited_by_count":4},{"id":"2009.02146","title":"Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games","created":"2020-09-02","cited_by_count":4},{"id":"2406.13992","title":"Robust Cooperative Multi-Agent Reinforcement Learning:A Mean-Field Type Game Perspective","created":"2024-06-20","cited_by_count":4},{"id":"2604.27378","title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","created":"2026-04-30","cited_by_count":4},{"id":"2001.00925","title":"McKean-Vlasov optimal control: limit theory and equivalence between different formulations","created":"2020-01-03","cited_by_count":3},{"id":"2405.17017","title":"Analysis of Multiscale Reinforcement Q-Learning Algorithms for Mean Field Control Games","created":"2024-05-27","cited_by_count":3},{"id":"2601.12226","title":"Mean-Field Games Under Model Uncertainty","created":"2026-01-18","cited_by_count":3},{"id":"1912.06371","title":"Social Optima in Mean Field Linear-Quadratic-Gaussian Control with Volatility Uncertainty","created":"2019-12-13","cited_by_count":2},{"id":"2006.12996","title":"Extended mean field control problem: a propagation of chaos result","created":"2020-06-19","cited_by_count":2},{"id":"2207.12738","title":"Quantitative propagation of chaos for mean field Markov decision process with common noise","created":"2022-07-26","cited_by_count":2},{"id":"2407.04259","title":"Q-Learning under Finite Model Uncertainty","created":"2024-07-05","cited_by_count":2},{"id":"2409.18152","title":"Reinforcement Learning for Finite Space Mean-Field Type Games","created":"2024-09-25","cited_by_count":2},{"id":"2410.11652","title":"Markov-Nash equilibria in mean-field games under model uncertainty","created":"2024-10-15","cited_by_count":2},{"id":"2511.04515","title":"Robust mean-field control under common noise uncertainty","created":"2025-11-06","cited_by_count":2},{"id":"2505.19058","title":"Distributionally Robust Deep Q-Learning","created":"2025-05-25","cited_by_count":1}],"next_cursor":null}