Metraipolis › archive › dc_c8d6ee01cfb7

ExactVariance of Random Return in Distributional LQR and Its Application to Mean-Variance Optimal Control — arXiv:2609.39981

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39981
License (as archived)
CC0-1.0
Archived
2026-10-07T14:11:29.009Z
SHA-256 of the archived text
9fa9e27497df96f82d4339c8a33aaad7452cc18b7604fead86dbc49b3dd881ea
Stable URL of this page
https://metraipolis.com/documento/dc_c8d6ee01cfb7

How to cite

ExactVariance of Random Return in Distributional LQR and Its Application to Mean-Variance Optimal Control — arXiv:2609.39981 — arXiv (en), https://arxiv.org/abs/2609.39981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8d6ee01cfb7 (Metraipolis archive dc_c8d6ee01cfb7, sha256 9fa9e27497df96f82d4339c8a33aaad7452cc18b7604fead86dbc49b3dd881ea)
BibTeX
@misc{dcc8d6ee01cfb7,
  title = {ExactVariance of Random Return in Distributional LQR and Its Application to Mean-Variance Optimal Control — arXiv:2609.39981},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39981},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8d6ee01cfb7; sha256 9fa9e27497df96f82d4339c8a33aaad7452cc18b7604fead86dbc49b3dd881ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The classical linear quadratic regulator (LQR) minimizes the expected cumulative return but fails to account for performance variability, rendering it inadequate for risk-aware applications. To address this, we introduce the variance of the cumulative return as a risk measure in LQR. We derive the first exact closed-form expression for the variance of the discounted in?finite horizon return within the discrete-time Distributional LQR framework, for i.i.d. disturbances with symmetric probability densities. For Gaussian disturbances, this expression elegantly simplifies to a form dependent only on the disturbance covariance. Leveraging these theoretical foundations, we formulate a mean-variance optimal control problem that explicitly manages the trade-off between expected return and performance variability. To address the resulting non-convex optimization problem, we propose a novel adjoint gradient descent algorithm for a penalized formulation of the original problem, and establish that all iterates remain stabilizing and converge to a stationary point of the penalized objective. The effectiveness of this framework and the inherent risk-performance trade-off? are demonstrated through numerical experiments.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-01 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.39981 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T14:03:18.269Z dalla pagina https://arxiv.org/catchup/math.OC/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).