Paper: arXiv 2305.15364

Authors: Hanchao Liu, Dena Firoozi, Michèle Breton

Abstract

We develop a variational approach to address risk-sensitive optimal control problems with an exponential-of-integral cost functional in a general linear-quadratic-Gaussian (LQG) single-agent setup, offering new insights into such problems. Our analysis leads to the derivation of a nonlinear necessary and sufficient condition of optimality, expressed in terms of martingale processes. Subject to specific conditions, we find an equivalent risk-neutral measure, under which a linear state feedback form can be obtained for the optimal control. It is then shown that the obtained feedback control is consistent with the imposed condition and remains optimal under the original measure. Building upon this development, we (i) propose a variational framework for general LQG risk-sensitive mean-field games (MFGs) and (ii) advance the LQG risk-sensitive MFG theory by incorporating a major agent in the framework. The major agent interacts with a large number of minor agents, and unlike the minor agents, its influence on the system remains significant even with an increasing number of minor agents. We derive the Markovian closed-loop best-response strategies of agents in the limiting case where the number of agents goes to infinity. We establish that the set of obtained best-response strategies yields a Nash equilibrium in the limiting case and an $\varepsilon$-Nash equilibrium in the finite-player case.

Complexity vs Empirical Score

  • Math Complexity: 9.2/10
  • Empirical Rigor: 1.5/10
  • Quadrant: Lab Rats — theoretically deep, empirically untested

Why this score: This paper presents a highly sophisticated theoretical expansion of LQG risk-sensitive control and mean-field games via a variational framework. While it is mathematically dense, rigorous, and novel, it is purely theoretical with no empirical backtesting or market data validation.

Research Flowchart

  flowchart TD
    A["Research Goal:<br>Develop variational framework for LQG Risk-Sensitive Single-Agent & Major-Minor MFGs"] --> B["System Inputs:<br>Linear-Quadratic-Gaussian dynamics & Exponential-of-integral cost functionals"]
    
    B --> C["Step 1: Single-Agent Variational Analysis<br>Derive martingale optimality condition & Change to risk-neutral measure"]
    
    C --> D["Step 2: Linear State Feedback Control<br>Obtain optimal control under risk-neutral measure & verify under original measure"]
    
    D --> E["Step 3: Extend to Major-Minor MFGs<br>Model asymmetric interactions between 1 major agent & N minor agents as N → ∞"]
    
    E --> F["Outcomes:<br>Markovian closed-loop best-response strategies yielding exact Nash (infinite) & ε-Nash (finite) equilibria"]