Policy Learning for Perturbance-wise Linear Quadratic Control Problem

We study finite horizon linear quadratic control with additive noise in a perturbancewise framework that unifies the classical model, a constraint embedded affine policy class, and a distributionally robust formulation with a Wasserstein ambiguity set. Based on an augmented affine representation, we model feasibility as an affine perturbation and unknown noise as distributional perturbation from samples, thereby addressing constrained implementation and model uncertainty in a single scheme. First, we construct an implementable policy gradient method that accommodates nonzero noise means estimated from data. Second, we analyze its convergence under constant stepsizes chosen as simple polynomials of problem parameters, ensuring global decrease of the value function. Finally, numerical studies: mean variance portfolio allocation and dynamic benchmark tracking on real data, validating stable convergence and illuminating sensitivity tradeoffs across horizon length, trading cost intensity, state penalty scale, and estimation window.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-11-10

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 2511.07388
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Data-Driven Long-Term Asset Allocation with Tsallis Entropy Regularization

  2025cited by this paper
• Wasserstein distributionally robust regret-optimal control over infinite-horizon

  2024cited by this paper
• Distributionally Robust Linear Quadratic Control

  2023cited by this paper
• Distributional robustness in minimax linear quadratic control with Wasserstein distance

  2021cited by this paper
• High‐dimensional Statistics: A Non‐asymptotic Viewpoint, Martin J.Wainwright, Cambridge University Press, 2019, xvii 552 pages, £57.99, hardback ISBN: 978‐1‐1084‐9802‐9

  2020influential reference
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon

  2020cited by this paper
• Explicit Solution for Constrained Scalar-State Stochastic Linear-Quadratic Control With Multiplicative Noise

  2019cited by this paper
• Optimization Methods for Financial Index Tracking: From Theory to Practice

  2018cited by this paper
• Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator

  2018cited by this paper
• Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

  2018cited by this paper
• On the Sample Complexity of the Linear Quadratic Regulator

  2017cited by this paper
• Dynamic Portfolio Choice with Linear Rebalancing Rules

  2017cited by this paper
• Optimal multi-period mean-variance policy under no-shorting constraint

  2014cited by this paper
• On the rate of convergence in Wasserstein distance of the empirical measure

  2013influential reference
• Dynamic Trading with Predictable Returns and Transaction Costs

  2013cited by this paper
• Stabilizing polynomial approximation of explicit MPC

  2011cited by this paper
• Duality for rectified cost functions

  2010cited by this paper
• Analytical expression of explicit MPC solution via lattice piecewise-affine function

  2009cited by this paper
• Tracking a Financial Benchmark Using a Few Assets

  2006cited by this paper
• The explicit linear quadratic regulator for constrained systems

  2003cited by this paper
• Technical Communique: Evaluation of piecewise affine control via binary search tree

  2003cited by this paper
• Portfolio Selection

  1971cited by this paper
• On a Matrix Riccati Equation of Stochastic Control

  1968cited by this paper
• Contributions to the Theory of Optimal Control

  1960cited by this paper

• No citing papers are available for this paper.