Pith. sign in

REVIEW 8 cited by

Learning in Mean Field Games: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2205.12944 v4 pith:NAHBDSF5 submitted 2022-05-25 cs.LG cs.AIcs.GTmath.OC

classification cs.LGcs.AIcs.GTmath.OC
keywords gamesmfgsmethodsnumberplayerssolvefieldgenerally
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Non-cooperative and cooperative games with a very large number of players have many applications but remain generally intractable when the number of players increases. Introduced by Lasry and Lions, and Huang, Caines and Malham\'e, Mean Field Games (MFGs) rely on a mean-field approximation to allow the number of players to grow to infinity. Traditional methods for solving these games generally rely on solving partial or stochastic differential equations with a full knowledge of the model. Recently, Reinforcement Learning (RL) has appeared promising to solve complex problems at scale. The combination of RL and MFGs is promising to solve games at a very large scale both in terms of population size and environment complexity. In this survey, we review the quickly growing recent literature on RL methods to learn equilibria and social optima in MFGs. We first identify the most common settings (static, stationary, and evolutive) of MFGs. We then present a general framework for classical iterative methods (based on best-response computation or policy evaluation) to solve MFGs in an exact way. Building on these algorithms and the connection with Markov Decision Processes, we explain how RL can be used to learn MFG solutions in a model-free way. Last, we present numerical illustrations on a benchmark problem, and conclude with some perspectives.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 13 citations worldwide. Full citation record

  1. Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games

    math.OC 2025-06 accept novelty 7.0 of 10

    A bilevel policy optimization algorithm for continuous-time linear-quadratic graphon mean field games converges linearly to best-response policies and globally to the Nash equilibrium.

  2. Neural operator learning for collision-aware trajectory planning of spacecraft swarms

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A self-supervised, permutation-equivariant neural operator trained on ten spacecraft generalizes zero-shot to 1,000-spacecraft swarms amid dense debris, with a Gauss–Newton finish enforcing two-body dynamics.

  3. Mean field and N-agent games for optimal relative consumption-investment with jump risk and common noise

    math.OC 2026-07 conditional novelty 6.0 of 10

    For competitive investors facing common noise and downward jumps, explicit mean-field equilibrium investment and consumption strategies are derived and shown to form an approximate Nash equilibrium.

  4. Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion

    cs.LG 2026-07 conditional novelty 6.0 of 10

    In a linear model of LLM personalization with shared compute, SFT beats ICL above a coverage-dependent signal-to-noise threshold, congestion can reverse that ranking, and adding SFT never reduces platform profit.

  5. Linear-Quadratic Mean Field Games with Hybrid Local-Global Interactions on Manifolds

    math.OC 2026-07 conditional novelty 6.0 of 10

    LQ mean-field games on hybrid manifold graphs admit FBPDE Nash limits with high-probability tracking error O((log N)^{-1/2}) sparse and O(N^{-γ(p,s)}) dense.

  6. Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)

    cs.GT 2025-08 conditional novelty 6.0 of 10

    In anonymous polymatrix games, fictitious play can be run on aggregate action counts without changing agents' best responses or losing convergence to Nash equilibrium.

  7. Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games

    stat.ML 2025-05 conditional novelty 6.0 of 10

    Exact and sample-based trust-region policy optimization provably converge to approximate Nash equilibria in finite mean-field games with Õ(1/ε^6) sample complexity.

  8. All in One: Generative Modeling as Mean-Field Game Design

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A unified library that expresses twelve generative models as one mean-field-game cost tuple, plus a new KDE-entropy interaction term and solver stack.

Pith tools