math.OC · 2607.12135 Copy arXiv ID · Jul 13, 2026 Save LQG solution for POMDP without estimating states: A minimum variance approach Authors: Ranjan Sarkar , Prabhat K. Mishra
Organizations: Department of Artificial Intelligence at Indian Institute of Technology Kharagpur, West Bengal, India
Abstract This paper investigates the control of discrete-time linear time-invariant (LTI) systems subject to incomplete and corrupted measurements. Specifically, we focus on designing a Linear Quadratic Gaussian (LQG) controller without relying on explicit state estimation. By leveraging minimum variance duality, our approach allows the current control input to be represented as a linear function of available measurements and previously applied inputs, successfully reducing the task to a tractable deterministic optimization problem. We provide theoretical justification for this framework and demonstrate its practical effectiveness through numerical experiments.
Explore similar work Aug 11, 2026 · Bangyan Liao, Chenglei Yu, Yuchen Yang +4 Stochastic Optimal Control Feynman-Kac
Feb 20, 2025 · Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard Linear Quadratic Regulator Lyapunov Function
Mar 19, 2026 · Vincent Pacelli, Evangelos A. Theodorou Feedback Linearization State Estimation
Aug 11, 2026 · cs.LG J/K move · Enter open · S save
Bangyan Liao, Chenglei Yu, Yuchen Yang, Chuanrui Wang +3
Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained renewed interest in the machine learning community. However, current state-of-the-art policy-based methods suffer from prohibitive computational costs and instability due to their heavy reliance on full-trajectory simulation. To overcome these limitations, we propose a paradigm shift toward a value-based approach by revisiting Path Integral Control (PIC). Although standard PIC suffers from the same high-variance bottleneck as policy-based methods, we discover that by truncating and marginalizing the original path integral formulation, we can derive a temporal recursive form of the value function. Building upon this theoretical foundation, we propose the Path Integral Value Matching (PI-VM) algorithm. Specifically, we employ temporal-difference learning to approximate the recursive value dynamics, and further integrate the Girsanov theorem with experience replay to enable off-policy training. We benchmark PI-VM against SOTA policy-based methods across various SOC benchmarks and sampling tasks. Empirical results demonstrate that PI-VM matches SOTA precision with an order-of-magnitude efficiency gain in low-dimensional settings, while effectively mitigating mode collapse in high-dimensional scenarios. Consequently, PI-VM offers a scalable solution for solving complex SOC problems.