Deep fictitious play for stochastic differential games
From MaRDI portal
(Redirected from Publication:2057010)
Abstract: In this paper, we apply the idea of fictitious play to design deep neural networks (DNNs), and develop deep learning theory and algorithms for computing the Nash equilibrium of asymmetric -player non-zero-sum stochastic differential games, for which we refer as emph{deep fictitious play}, a multi-stage learning process. Specifically at each stage, we propose the strategy of letting individual player optimize her own payoff subject to the other players' previous actions, equivalent to solve decoupled stochastic control optimization problems, which are approximated by DNNs. Therefore, the fictitious play strategy leads to a structure consisting of DNNs, which only communicate at the end of each stage. The resulted deep learning algorithm based on fictitious play is scalable, parallel and model-free, {it i.e.}, using GPU parallelization, it can be applied to any -player stochastic differential game with different symmetries and heterogeneities ({it e.g.}, existence of major players). We illustrate the performance of the deep learning algorithm by comparing to the closed-form solution of the linear quadratic game. Moreover, we prove the convergence of fictitious play under appropriate assumptions, and verify that the convergent limit forms an open-loop Nash equilibrium. We also discuss the extensions to other strategies designed upon fictitious play and closed-loop Nash equilibrium in the end.
Recommendations
- Convergence of deep fictitious play for stochastic differential games
- Fictitious play in zero-sum stochastic games
- Deep Q-Learning for Nash Equilibria: Nash-DQN
- Sampled fictitious play for approximate dynamic programming
- A dynamical neural network approach for solving stochastic two-player zero-sum games
Cited in
(20)- Recurrent neural networks for stochastic control problems with delay
- A game-theoretic perspective of deep neural networks
- A game-theoretic analysis of deep neural networks
- Convergence of deep fictitious play for stochastic differential games
- Sampled fictitious play for approximate dynamic programming
- Deep Q-Learning for Nash Equilibria: Nash-DQN
- A class of dimension-free metrics for the convergence of empirical measures
- Deep neural network solution for finite state mean field game with error estimation
- Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems
- Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence
- Dynamics of market making algorithms in dealer markets: Learning and tacit collusion
- Game on Random Environment, Mean-Field Langevin System, and Neural Networks
- Data-driven stability of stochastic mean-field type games via noncooperative neural network adversarial training
- Non-zero-sum differential games of delayed backward doubly stochastic systems and their application
- Recent developments in machine learning methods for stochastic control and games
- Finite-agent stochastic differential games on large graphs. I: The linear-quadratic case
- Multiagent relative investment games in a jump diffusion market with deep reinforcement learning algorithm
- Finite-agent stochastic differential games on large graphs. II: Graph-based architectures
- DeepHAM: a global solution method for heterogeneous agent models with aggregate shocks
- Deep Truncated FBSDE Method: A Robust Solver for High-Dimensional Nonlinear PDEs and Fully Coupled FBSDEs
This page was built for publication: Deep fictitious play for stochastic differential games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057010)
