Learning Mean-Field Games through Mean-Field Actor-Critic Flow
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
We propose the Mean-Field Actor-Critic (MFAC) flow, a continuous-time learning dynamics for solving mean-field games (MFGs), combining techniques from reinforcement learning and optimal transport. The MFAC framework jointly evolves the control (actor), value function (critic), and distribution components through coupled gradient-based updates governed by partial differential equations (PDEs). A central innovation is the Optimal Transport Geodesic Picard (OTGP) flow, which drives the distribution toward equilibrium along Wasserstein-2 geodesics. We conduct a rigorous convergence analysis using Lyapunov functionals and establish global exponential convergence of the MFAC flow under a suitable timescale. Our results highlight the algorithmic interplay among actor, critic, and distribution components. Numerical experiments illustrate the theoretical findings and demonstrate the effectiveness of the MFAC framework in computing MFG equilibria.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 14 Oct 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
- 2024Efficient and Scalable Deep Reinforcement Learning for Mean Field Control Games
- 2024Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis
- 2026Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies
- 2025Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games
- 2025Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
- 2026Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
- 2025Computing and Learning Stationary Mean Field Equilibria with Low-Dimensional Interactions: Algorithms and Applications ↗