Stochastic Trajectory Influence Functions for LQR: Joint Sensitivity Through Dynamics and Noise Covariance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jiachen, Li, Shihao, Bakshi, Soovadeep, Xu, Jiamin, Chen, Dongmei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917357675347968
author Li, Jiachen
Li, Shihao
Bakshi, Soovadeep
Xu, Jiamin
Chen, Dongmei
author_facet Li, Jiachen
Li, Shihao
Bakshi, Soovadeep
Xu, Jiamin
Chen, Dongmei
contents Model-based controllers learned from data have the biases and noise of their training trajectories, making it important to know which trajectories help or hurt closed-loop performance. Influence functions, widely used in machine learning for data attribution, approximate this effect through first-order parameter-shift surrogates, avoiding costly retraining. Applying them to stochastic LQR, however, is nontrivial because the cost depends on the learned dynamics through the Riccati equation, and the process-noise covariance is estimated from the same residuals. We develop a three-level influence hierarchy that accounts for both channels.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21539
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stochastic Trajectory Influence Functions for LQR: Joint Sensitivity Through Dynamics and Noise Covariance
Li, Jiachen
Li, Shihao
Bakshi, Soovadeep
Xu, Jiamin
Chen, Dongmei
Systems and Control
Model-based controllers learned from data have the biases and noise of their training trajectories, making it important to know which trajectories help or hurt closed-loop performance. Influence functions, widely used in machine learning for data attribution, approximate this effect through first-order parameter-shift surrogates, avoiding costly retraining. Applying them to stochastic LQR, however, is nontrivial because the cost depends on the learned dynamics through the Riccati equation, and the process-noise covariance is estimated from the same residuals. We develop a three-level influence hierarchy that accounts for both channels.
title Stochastic Trajectory Influence Functions for LQR: Joint Sensitivity Through Dynamics and Noise Covariance
topic Systems and Control
url https://arxiv.org/abs/2603.21539