{"total":31,"rows":[{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101,"area":null},{"id":"2108.06655","title":"Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach","created":"2021-08-15","cited_by_count":84,"area":null},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38,"area":null},{"id":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","cited_by_count":28,"area":null},{"id":"2304.13534","title":"A mean-field games laboratory for generative modeling","created":"2023-04-26","cited_by_count":28,"area":null},{"id":"2212.14449","title":"Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games","created":"2022-12-29","cited_by_count":26,"area":null},{"id":"2104.09311","title":"Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls","created":"2021-04-19","cited_by_count":24,"area":null},{"id":"2303.06993","title":"Actor-Critic learning for mean-field control in continuous time","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"2306.16208","title":"Continuous-time q-learning for mean-field control problems","created":"2023-06-28","cited_by_count":22,"area":null},{"id":"2112.10264","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","created":"2021-12-19","cited_by_count":21,"area":null},{"id":"2108.10403","title":"Robust Risk-Aware Reinforcement Learning","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2209.03880","title":"Learning Sparse Graphon Mean Field Games","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2302.05816","title":"A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee","created":"2023-02-11","cited_by_count":10,"area":null},{"id":"2312.11797","title":"Data-Driven Merton's Strategies via Policy Randomization","created":"2023-12-19","cited_by_count":8,"area":null},{"id":"2208.04466","title":"Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2309.10953","title":"Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces","created":"2023-09-19","cited_by_count":6,"area":null},{"id":"2406.10959","title":"Convergence Analysis for Entropy-Regularized Control Problems: A Probabilistic Approach","created":"2024-06-16","cited_by_count":6,"area":null},{"id":"2303.04833","title":"Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning","created":"2023-02-24","cited_by_count":4,"area":null},{"id":"2203.16223","title":"Hypergraphon Mean Field Games","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2401.12686","title":"Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2503.21224","title":"Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2208.08497","title":"Choquet regularization for reinforcement learning","created":"2022-08-17","cited_by_count":2,"area":null},{"id":"2312.10787","title":"Learning Discrete-Time Major-Minor Mean Field Games","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2404.00045","title":"Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2405.03718","title":"A Single Online Agent Can Efficiently Learn Mean Field Games","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2306.02766","title":"Networked Communication for Decentralised Agents in Mean-Field Games","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2411.07099","title":"Bounded Rationality Equilibrium Learning in Mean Field Games","created":"2024-11-11","cited_by_count":0,"area":null}],"next_cursor":null}