AI News HubLIVE
原文

Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction

This paper proposes behavior-aware auxiliary corrections to stabilize off-policy temporal-difference learning. By replacing the auxiliary covariance matrix with the behavior Bellman matrix, the authors introduce BA-TDC and BA-TDRC algorithms. Theoretical analysis proves fixed-point preservation and almost-sure convergence. Experiments on standard benchmarks show that the behavior-aware replacement improves performance, but regularization is needed for robust results.

Article intelligence

EngineersAdvanced

Key points

  • Behavior-aware auxiliary corrections improve stability of off-policy TD learning.
  • BA-TDC and BA-TDRC replace the auxiliary covariance matrix with the behavior Bellman matrix.
  • Theoretical convergence guarantees are provided under a Hurwitz stability condition.
  • Experimental results on counterexamples and random walk demonstrate effectiveness.

Why it matters

This matters because behavior-aware auxiliary corrections improve stability of off-policy TD learning.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.28855] Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction

[Submitted on 17 May 2026]

Title:Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction

View a PDF of the paper titled Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction, by Xingguo Chen and 6 other authors

View PDF HTML (experimental)

Abstract: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_\mu), 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.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.28855 [cs.AI]

(or arXiv:2605.28855v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.28855

arXiv-issued DOI via DataCite

Submission history

From: Xingguo Chen [view email] [v1] Sun, 17 May 2026 08:49:52 UTC (5,392 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction, by Xingguo Chen and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)