Mean Field Reinforcement Learning: Theory and Algorithms for Mean Field Control
math.OC, cs.LG, cs.MA, math.PR
Submitted: 2026-07-01
Updated: 2026-11-01
Code: https://github.com/mlauriere/mfrl-tutorial-code
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Convergence of Multi-Scale Reinforcement Q-Learning Algorithms for Mean Field Game and Control Problems
- Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data
- Lyapunov Theory for Discrete Time Systems
- Reconciling Discrete-Time Mixed Policies and Continuous-Time Relaxed Controls in Reinforcement Learning and Stochastic Control
- A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning
- Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise
- Learning in Mean Field Games: A Survey
- Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach
- Model-free policy gradient for discrete-time mean-field control
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Propagation of Chaos for Nonlinear Markov Chains
- Robust Mean Field Social Control: A Unified Reinforcement Learning Framework
- Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise