{"total":59,"rows":[{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38,"area":null},{"id":"2109.04024","title":"On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)","created":"2021-09-09","cited_by_count":32,"area":null},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28,"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":"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":"2106.13755","title":"Reinforcement Learning for Mean Field Games, with Applications to Economics","created":"2021-06-25","cited_by_count":15,"area":null},{"id":"2105.08268","title":"Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach","created":"2021-05-18","cited_by_count":14,"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":"2301.06889","title":"Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Non-decomposable Shared Global State","created":"2023-01-13","cited_by_count":8,"area":null},{"id":"2403.00222","title":"Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale","created":"2024-03-01","cited_by_count":8,"area":"deeprl"},{"id":"2307.06175","title":"Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior","created":"2023-07-12","cited_by_count":7,"area":null},{"id":"2309.04317","title":"Actor critic learning algorithms for mean-field control with moment neural networks","created":"2023-09-08","cited_by_count":7,"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":"2406.06823","title":"Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2408.02489","title":"Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise","created":"2024-08-05","cited_by_count":6,"area":"deeprl"},{"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,"area":"deeprl"},{"id":"2212.07684","title":"Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management","created":"2022-12-15","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":"2306.17052","title":"Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2310.17531","title":"Learning Regularized Graphon Mean-Field Games with Unknown Graphons","created":"2023-10-26","cited_by_count":4,"area":null},{"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":"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,"area":"deeprl"},{"id":"2107.00839","title":"Exploration noise for learning linear-quadratic mean field games","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2203.16223","title":"Hypergraphon Mean Field Games","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2403.11345","title":"Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective","created":"2024-03-17","cited_by_count":3,"area":"deeprl"},{"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":"2504.21793","title":"Reconciling Discrete-Time Mixed Policies and Continuous-Time Relaxed Controls in Reinforcement Learning and Stochastic Control","created":"2025-04-30","cited_by_count":3,"area":"deeprl"},{"id":"2506.07856","title":"Stability of Mean-Field Variational Inference","created":"2025-06-09","cited_by_count":3,"area":null},{"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":"2603.09571","title":"An Optimal Control Approach To Transformer Training","created":"2026-03-10","cited_by_count":3,"area":null},{"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":"2405.03718","title":"A Single Online Agent Can Efficiently Learn Mean Field Games","created":"2024-05-05","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":"2501.17079","title":"Learning Mean Field Control on Sparse Graphs","created":"2025-01-28","cited_by_count":2,"area":"deeprl"},{"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":"2312.12977","title":"Collaborative Optimization of the Age of Information under Partial Observability","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2410.08850","title":"Learning to Stop: Deep Learning for Mean Field Optimal Stopping","created":"2024-10-11","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":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2602.16196","title":"Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2606.26498","title":"Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data","created":"2026-06-25","cited_by_count":1,"area":"deeprl"},{"id":"2607.11005","title":"Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies","created":"2026-07-13","cited_by_count":1,"area":"deeprl"},{"id":"2304.12458","title":"Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout","created":"2023-04-24","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":"2501.17801","title":"Consensus Based Stochastic Control","created":"2025-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2503.24183","title":"Scalable Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantee: A Constrained Mean-Field Reinforcement Learning Approach","created":"2025-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2509.15103","title":"Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2603.27137","title":"A Mean Field Games Perspective on Evolutionary Clustering","created":"2026-03-28","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}],"next_cursor":null}