mlsanityData to 14 Oct 2026

Robust policy iteration for continuous-time stochastic H_∞ control problem with unknown dynamics

arXiv 2402.04721 ↗First posted 7 Feb 2024math.OCcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

In this article, we study a continuous-time stochastic H_∞ control problem based on reinforcement learning (RL) techniques that can be viewed as solving a stochastic linear-quadratic two-person zero-sum differential game (LQZSG). First, we propose an RL algorithm that can iteratively solve stochastic game algebraic Riccati equation based on collected state and control data when all dynamic system information is unknown. In addition, the algorithm only needs to collect data once during the iteration process. Then, we discuss the robustness and convergence of the inner and outer loops of the policy iteration algorithm, respectively, and show that when the error of each iteration is within a certain range, the algorithm can converge to a small neighborhood of the saddle point of the stochastic LQZSG problem. Finally, we applied the proposed RL algorithm to two simulation examples to verify the effectiveness of the algorithm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 7 of its 32 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

7 of 32 references.

References · 7

  1. 2021Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithmscited by 101
  2. 2020Entropy Regularization for Mean Field Games with Learningcited by 58
  3. 2020Robust Policy Iteration for Continuous-time Linear Quadratic Regulationcited by 15
  4. 2020Exploratory LQG Mean Field Games with Entropy Regularizationcited by 15
  5. 2020Stochastic Linear Quadratic Optimal Control Problem: A Reinforcement Learning Methodcited by 11
  6. 2021Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systemscited by 8
  7. 2014Linear Quadratic Stochastic Two-Person Zero-Sum Differential Games in an Infinite Horizoncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reinforcement Learning Method for Zero-Sum Linear-Quadratic Stochastic Differential Games in Infinite Horizons
  2. 2025Computing stabilizing feedback gains for stochastic linear systems via policy iteration method ↗
  3. 2025A Fully Data-Driven Value Iteration for Stochastic LQR: Convergence, Robustness and Stability
  4. 2025Reinforcement Learning for Discrete-time LQG Mean Field Social Control Problems with Unknown Dynamics
  5. 2025Robust Mean Field Social Control: A Unified Reinforcement Learning Framework
  6. 2024Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems
  7. 2025Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression
  8. 2024Model-free H∞ control of Ito stochastic system via off-policy reinforcement learning