CORTEXA
← Browse
arxiveess.SY2026-07-16

Consistent Variance Estimation for Q-Function Estimators in Finite-Horizon MDP Tree Search

Zhenyu Yue, Jie Xu, Chun-Hung Chen, Hadi El-Amine, Michael C. Fu

We study the variance of Q-function estimators in finite-horizon, finite-state Markov decision process (MDP) tree search. We show that the variance decomposes into three components attributed to the immediate reward collected, probabilistic state transitions, and uncertainty in future state value function estimates. Using this decomposition, we show that the sample variance estimator based on the assumption of i.i.d. paths is biased, underestimating the true variance, and the bias does not vanish in the limit. We then propose a recursive variance estimator that is consistent. To enable efficient storage and computation, we derive an equivalent implementation of the recursive estimator using only node-local statistics that can be iteratively updated. This consistent variance estimator is integrated into two Monte Carlo Tree Search (MCTS) sampling procedures for finite-horizon MDPs. In numerical examples from inventory control and kidney paired donation matching, the new estimator improves the performance of the MCTS algorithm relative to a baseline that uses the i.i.d.-based sample variance estimator.

View free PDFSource page

Related papers

arxiveess.SY2026-07-20

Real-Time Flight Test Maneuver Selection with Monte Carlo Tree Search

Nicholas E. Bostock, Helen Pruitt-Kennett, Marc R. Schlichting, Mykel J. Kochenderfer

Flight test is shifting toward a data-centric approach in which data contribute to model refinement, reducing reliance on pre-scripted test points. An open problem is how to sequence maneuvers within a sortie to maximize uncertainty reduction under resource limits. We present a r…

View free PDFSource page
arxivcs.LGeess.SY2026-07-24

Variance-Reduced Q-Learning over Static and Time-Varying Networks

Sreejeet Maity, Feng Zhu, Aritra Mitra, Robert W. Heath

We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The agents can exchange information over a network to collectively learn the optimal state-action value function. For this setting, w…

View free PDFSource page
arxivmath.OCcs.ROeess.SY2026-07-13

LQG solution for POMDP without estimating states: A minimum variance approach

Ranjan Sarkar, Prabhat K. Mishra

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…

View free PDFSource page
arxiveess.SY2026-07-19

A recursive subspace based method for errors-in-variables model identification of time-varying systems

Deepanjhan Das, Shankar Narasimhan

The Subspace-based Model Identification algorithm using a modified Iterative Principal Component Analysis (SMI-IPCA) is a theoretically rigorous method for identifying a linear state-space model of a multi-input multi-output (MIMO) process, in an errors-in-variables (EIV) setting…

View free PDFSource page
arxiveess.SY2026-07-16

Finite-Sample Conformal Coverage Recovery via Fusion under Degraded Local Guarantees in Occupancy Map Estimation

Ritvik Mahajan, Aneesh Raghavan, Karl Henrik Johansson

Accurate and reliable environmental mapping is a fundamental requirement for multi-robot autonomy. While continuous mapping techniques like Gaussian Process Occupancy Mapping (GPOM) provide rich spatial correlation and uncertainty estimates, they lack formal, finite-sample guaran…

View free PDFSource page
arxiveess.SY2026-07-17

Dynamic Constraint Reconstruction Based Control Barrier Functions for Safety-Critical Control of High-Dimensional Manipulators

Bingsheng Zhang, Shen Wang, Qiang Wang, Muguo Du, Donghai Shi, Xiaofeng Tao

Control barrier functions (CBFs) provide formal safety guarantees for constrained nonlinear systems, but their effectiveness relies on accurate system dynamics. In high-dimensional manipulators subject to unknown disturbances and model uncertainties, fixed safety constraints cons…

View free PDFSource page