Exploratory LQG mean field games with entropy regularization
From MaRDI portal
Publication:2116646
DOI10.1016/J.AUTOMATICA.2022.110177zbMATH Open1484.91037arXiv2011.12946OpenAlexW3110347183MaRDI QIDQ2116646FDOQ2116646
Authors: Dena Firoozi, Sebastian Jaimungal 
Publication date: 18 March 2022
Published in: Automatica (Search for Journal in Brave)
Abstract: We study a general class of entropy-regularized multi-variate LQG mean field games (MFGs) in continuous time with distinct sub-population of agents. We extend the notion of actions to action distributions (exploratory actions), and explicitly derive the optimal action distributions for individual agents in the limiting MFG. We demonstrate that the optimal set of action distributions yields an -Nash equilibrium for the finite-population entropy-regularized MFG. Furthermore, we compare the resulting solutions with those of classical LQG MFGs and establish the equivalence of their existence.
Full work available at URL: https://arxiv.org/abs/2011.12946
Recommendations
- Entropy Regularization for Mean Field Games with Learning
- Explicit solutions of some linear-quadratic mean field games
- \(\epsilon\)-Nash mean-field games for general linear-quadratic systems with applications
- LQG mean field games with a major agent: Nash certainty equivalence versus probabilistic approach
- Q-learning in regularized mean-field games
Cites Work
- Mean field games
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Large-population LQG games involving a major player: the Nash certainty equivalence principle
- The Variational Formulation of the Fokker--Planck Equation
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
- Mean field games and mean field type control theory
- Mean field games. I: The stationary case
- Mean field games. II: Finite horizon and optimal control
- \(\epsilon\)-Nash mean field game theory for nonlinear stochastic dynamical systems with major and minor agents
- Mean field games and systemic risk
- Mean-field games with a major player
- Entropy penalization methods for Hamilton-Jacobi equations
- The Master Equation and the Convergence Problem in Mean Field Games
- Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
- Mean field game theory with a partially observed major agent
- Exponential convergence and stability of Howard's policy improvement algorithm for controlled diffusions
- Linear-quadratic-Gaussian mean-field-game with partial observation and common noise
- The execution problem in finance with major and minor traders: a mean field game formulation
- Mean-field games of optimal stopping: a relaxed solution approach
- Linear-quadratic mean field Stackelberg games with state and control delays
- A Mean-Field Game of Evacuation in Multilevel Building
- An alternative approach to mean field game with major and minor players, and applications to herders impacts
- Learning in Mean-Field Games
- Title not available (Why is that?)
- An integral control formulation of mean field game based large scale coordination of loads in smart grids
- Value iteration algorithm for mean-field games
- Mean-field games with differing beliefs for algorithmic trading
- Mean-field controls with Q-learning for cooperative MARL: convergence and complexity analysis
- Continuous‐time mean–variance portfolio selection: A reinforcement learning framework
- Convex analysis for LQG systems with applications to major-minor LQG mean-field game systems
- $\epsilon$-Nash Equilibria for Major–Minor LQG Mean Field Games With Partial Observations of All Agents
- Remarks on Nash equilibria in mean field game models with a major player
- The Principle of Maximum Causal Entropy for Estimating Interacting Processes
- A framework for robust quadratic optimal control with parametric dynamic model uncertainty using polynomial chaos
Cited In (13)
- Reinforcement learning for continuous-time mean-variance portfolio selection in a regime-switching market
- Q-learning in regularized mean-field games
- Exploratory HJB equations and their convergence
- A class of hybrid LQG mean field games with state-invariant switching and stopping strategies
- Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning
- Entropy Regularization for Mean Field Games with Learning
- Recent developments in machine learning methods for stochastic control and games
- Exploratory Control with Tsallis Entropy for Latent Factor Models
- Deep Q-Learning for Nash Equilibria: Nash-DQN
- Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
- Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games
- Dual stochastic descriptions of streamflow dynamics under model ambiguity through a Markovian embedding
- Anderson acceleration for partially observable Markov decision processes: a maximum entropy approach
This page was built for publication: Exploratory LQG mean field games with entropy regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2116646)
