{"total":73,"rows":[{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"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":"2112.01280","title":"Learning Graphon Mean Field Games and Approximate Nash Equilibria","created":"2021-11-29","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":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24,"area":null},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"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":"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,"area":"deeprl"},{"id":"2202.06401","title":"Individual-Level Inverse Reinforcement Learning for Mean Field Games","created":"2022-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2306.14799","title":"On Imitation in Mean-field Games","created":"2023-06-26","cited_by_count":10,"area":"offlinerl"},{"id":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2402.05724","title":"Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL","created":"2024-02-08","cited_by_count":9,"area":"deeprl"},{"id":"2104.14654","title":"Adversarial Inverse Reinforcement Learning for Mean Field Games","created":"2021-04-29","cited_by_count":8,"area":"offlinerl"},{"id":"2402.05757","title":"When is Mean-Field Reinforcement Learning Tractable and Relevant?","created":"2024-02-08","cited_by_count":8,"area":"deeprl"},{"id":"2104.14900","title":"Discrete-Time Mean Field Control with Environment States","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2302.00797","title":"Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning","created":"2023-02-01","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":"2503.07324","title":"Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamics","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2303.03196","title":"Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2304.01547","title":"Regularization of the policy updates for stabilizing Mean Field Games","created":"2023-04-04","cited_by_count":5,"area":null},{"id":"2403.03552","title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning","created":"2024-03-06","cited_by_count":5,"area":"deeprl"},{"id":"2405.00282","title":"MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games","created":"2024-05-01","cited_by_count":5,"area":"deeprl"},{"id":"2405.08005","title":"Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2408.08192","title":"Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2303.10665","title":"Major-Minor Mean Field Multi-Agent Reinforcement Learning","created":"2023-03-19","cited_by_count":4,"area":null},{"id":"2401.06566","title":"Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL","created":"2024-01-12","cited_by_count":4,"area":"offlinerl"},{"id":"2410.15119","title":"Mean Field LQG Social Optimization: A Reinforcement Learning Approach","created":"2024-10-19","cited_by_count":4,"area":"deeprl"},{"id":"2509.03030","title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","created":"2025-09-03","cited_by_count":4,"area":"deeprl"},{"id":"2601.11217","title":"Model-free policy gradient for discrete-time mean-field control","created":"2026-01-16","cited_by_count":4,"area":"deeprl"},{"id":"2203.16223","title":"Hypergraphon Mean Field Games","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2209.03887","title":"Mean Field Games on Weighted and Directed Graphs via Colored Digraphons","created":"2022-09-08","cited_by_count":3,"area":null},{"id":"2302.03364","title":"Population-size-Aware Policy Optimization for Mean-Field Games","created":"2023-02-07","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":"2405.17017","title":"Analysis of Multiscale Reinforcement Q-Learning Algorithms for Mean Field Control Games","created":"2024-05-27","cited_by_count":3,"area":"deeprl"},{"id":"2408.04780","title":"Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis","created":"2024-08-08","cited_by_count":3,"area":"deeprl"},{"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":"2509.03845","title":"Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables","created":"2025-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2511.06812","title":"Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces","created":"2025-11-10","cited_by_count":3,"area":"deeprl"},{"id":"2208.04777","title":"Learning Mean-Field Control for Delayed Information Load Balancing in Large Queuing Systems","created":"2022-08-09","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":"2408.15173","title":"Exploiting Approximate Symmetry for Efficient Multi-Agent Reinforcement Learning","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2409.18152","title":"Reinforcement Learning for Finite Space Mean-Field Type Games","created":"2024-09-25","cited_by_count":2,"area":"deeprl"},{"id":"2411.14052","title":"Dynamic Trajectory and Power Control in Ultra-Dense UAV Networks: A Mean-Field Reinforcement Learning Approach","created":"2024-11-21","cited_by_count":2,"area":"deeprl"},{"id":"2505.22781","title":"Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.22158","title":"Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2602.13169","title":"Operator Learning for Families of Finite-State Mean-Field Games","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2209.07420","title":"Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2410.17898","title":"Scalable Offline Reinforcement Learning for Mean Field Games","created":"2024-10-23","cited_by_count":1,"area":"offlinerl"},{"id":"2506.05894","title":"Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2509.15392","title":"Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis","created":"2025-09-18","cited_by_count":1,"area":"deeprl"},{"id":"2602.12517","title":"Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games","created":"2026-02-13","cited_by_count":1,"area":"deeprl"},{"id":"2212.13379","title":"Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization","created":"2022-12-27","cited_by_count":0,"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":"2404.04357","title":"Why does the two-timescale Q-learning converge to different mean field solutions? A unified convergence analysis","created":"2024-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2404.09324","title":"Mean Field Correlated Imitation Learning","created":"2024-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2408.11607","title":"Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2410.05127","title":"Last Iterate Convergence in Monotone Mean Field Games","created":"2024-10-07","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},{"id":"2503.06037","title":"Vairiational Stochastic Games","created":"2025-03-08","cited_by_count":0,"area":"deeprl"},{"id":"2504.13228","title":"Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2507.01420","title":"Reinforcement Learning for Discrete-time LQG Mean Field Social Control Problems with Unknown Dynamics","created":"2025-07-02","cited_by_count":0,"area":"deeprl"},{"id":"2602.20141","title":"Recurrent Structural Policy Gradient for Partially Observable Mean Field Games","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2605.11042","title":"Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.20356","title":"Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.22579","title":"Stationary Robust Mean-Field Games under Model Mismatches","created":"2026-06-21","cited_by_count":0,"area":"deeprl"},{"id":"2610.02195","title":"Cost-augmented Schr\\\"odinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.09244","title":"Beyond Nominal Equilibria: Risk-Averse Multi-Population Mean-Field Games","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.15871","title":"Entropy-Regularized Mean-Field Games with Average-Reward Criterion: Span-Seminorm Contractions and Model-Free Learning","created":"2026-10-11","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}