Saved in:
Bibliographic Details
Main Authors: Chen, Xingguo, He, Zhiang, Shen, Yuchen, Yang, Shangdong, Li, Chao, Yang, Guang, Wang, Wenhao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.28855
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911725353172992
author Chen, Xingguo
He, Zhiang
Shen, Yuchen
Yang, Shangdong
Li, Chao
Yang, Guang
Wang, Wenhao
author_facet Chen, Xingguo
He, Zhiang
Shen, Yuchen
Yang, Shangdong
Li, Chao
Yang, Guang
Wang, Wenhao
contents Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale recursion. This paper studies a behavior-aware replacement of the auxiliary covariance geometry in the linear prediction setting, which is the standard local model for understanding the feature-space dynamics of value-function approximation. We first replace the TDC auxiliary matrix (C) by the behavior Bellman matrix (A_μ), yielding BA-TDC, and then regularize the same behavior-aware equation to obtain BA-TDRC. This two-step construction separates the contribution of behavior-aware geometry from the contribution of regularization. The linear analysis also provides a tractable model for an auxiliary-geometry design question that arises in neural-network value approximation, where feature covariances and temporal transition matrices jointly shape the last-layer correction dynamics. We give a finite-state mean-system formulation, prove fixed-point preservation and almost-sure convergence under a Hurwitz stability condition on the instantiated mean system, and compare deterministic mean rates through the spectral radius of the exact linear error recursion. Experiments on the two-state counterexample, Baird's counterexample, Random Walk, and Boyan Chain show that the behavior-aware replacement can be highly beneficial by itself on some tasks, but that regularization is necessary for robust performance across harder settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28855
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction
Chen, Xingguo
He, Zhiang
Shen, Yuchen
Yang, Shangdong
Li, Chao
Yang, Guang
Wang, Wenhao
Artificial Intelligence
Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale recursion. This paper studies a behavior-aware replacement of the auxiliary covariance geometry in the linear prediction setting, which is the standard local model for understanding the feature-space dynamics of value-function approximation. We first replace the TDC auxiliary matrix (C) by the behavior Bellman matrix (A_μ), yielding BA-TDC, and then regularize the same behavior-aware equation to obtain BA-TDRC. This two-step construction separates the contribution of behavior-aware geometry from the contribution of regularization. The linear analysis also provides a tractable model for an auxiliary-geometry design question that arises in neural-network value approximation, where feature covariances and temporal transition matrices jointly shape the last-layer correction dynamics. We give a finite-state mean-system formulation, prove fixed-point preservation and almost-sure convergence under a Hurwitz stability condition on the instantiated mean system, and compare deterministic mean rates through the spectral radius of the exact linear error recursion. Experiments on the two-state counterexample, Baird's counterexample, Random Walk, and Boyan Chain show that the behavior-aware replacement can be highly beneficial by itself on some tasks, but that regularization is necessary for robust performance across harder settings.
title Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2605.28855