mlsanityData to 14 Oct 2026

Quadratic Truncated Random Return in Distributional LQR: Positive Definiteness, Density, and Log-Concavity

arXiv 2510.23332 ↗First posted 27 Oct 2025math.OCcited by 0

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

Abstract (arXiv)

Distributional linear quadratic regulator (LQR) is a new framework that integrates the distributional reinforcement learning and classical LQR, which offers a new way to study the random return instead of the expected cost. Unlike iterative approximation using dynamic programming in the DRL, a closed-form expression for the random return can be exactly characterized in the distributional LQR, which is defined over infinitely many random variables. In recent work [1, 2], it has been shown that this random return can be well approximated by a finite number of random variables, which we call truncated random return. In this paper, we study the truncated random return in the distributional LQR. We show that the truncated random return can be naturally expressed in the quadratic form. We develop a sufficient condition for the positive definiteness of the block symmetric matrix in the quadratic form and provide the lower and upper bounds on the eigenvalues of this matrix. We further show that in this case, the truncated random return follows a positively weighted non-central chi-square distribution if the random disturbances admits Gaussian, and its cumulative distribution function is log-concave if the probability density function of the random disturbances is log-concave.

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 6 of its 26 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

6 of 26 references.

References · 6

  1. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  2. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  3. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
  4. 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 159
  5. 2018Log-concave sampling: Metropolis-Hastings algorithms are fastcited by 118
  6. 2023Policy Evaluation in Distributional LQR (Extended Version)cited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026(Cheap) Stochastic Policy Gradient Converges with High Probability for Linear Quadratic Regulator
  2. 2025Policy Gradient for LQR with Domain Randomization
  3. 2024Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
  4. 2024A Robust Quantile Huber Loss With Interpretable Parameter Adjustment In Distributional Reinforcement Learning
  5. 2025A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation
  6. 2026Policy Gradient over History-Dependent Policy Classes for LQR with Domain Randomization
  7. 2025Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression
  8. 2026Optimistic Online LQR via Intrinsic Rewards