Learning in Discounted-cost and Average-cost Mean-field Games
arXiv:1912.13309
Abstract
We consider learning approximate Nash equilibria for discrete-time mean-field games with nonlinear stochastic state dynamics subject to both average and discounted costs. To this end, we introduce a mean-field equilibrium (MFE) operator, whose fixed point is a mean-field equilibrium (i.e. equilibrium in the infinite population limit). We first prove that this operator is a contraction, and propose a learning algorithm to compute an approximate mean-field equilibrium by approximating the MFE operator with a random one. Moreover, using the contraction property of the MFE operator, we establish the error analysis of the proposed learning algorithm. We then show that the learned mean-field equilibrium constitutes an approximate Nash equilibrium for finite-agent games.
arXiv comment59 pages
References in corpus (6)
- Concentration inequalities for dependent Random variables via the martingale method
- Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning
- Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
- Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games
- Mean Field Games with Ergodic cost for Discrete Time Markov Processes
- Learning Deep Mean Field Games for Modeling Large Population Behavior