A bisection-based adaptive algorithm converges to a mean field equilibrium for scalar-interaction dynamic games, and a model-free Q-learning variant learns it from simulation.
The projected policy gradient update rule which is expressed as: σh+1 =P P(S×A) (σh +γ h∇σV(σ h)) (7) whereγ h denotes the learning rate at iterationh
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.TH 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Computing and Learning Stationary Mean Field Equilibria with Scalar Interactions: Algorithms and Applications
A bisection-based adaptive algorithm converges to a mean field equilibrium for scalar-interaction dynamic games, and a model-free Q-learning variant learns it from simulation.