Stability-Oriented Agentic Reinforcement Learning for Web Decision Systems under Cost and Failure Constraints
American Journal Of Big Data · 2026-03-25 · 7 (1) · 202-211
DOI: 10.71465/ajbd3655 ↗At a glance
Journal article in American Journal Of Big Data, published online on 2026-03-25. Written by Emily Chen and 2 co-authors. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Long-horizon web tasks often exhibit unstable behavior, where small decision errors propagate and lead to budget overruns or catastrophic failures. This study introduces a stability-oriented formulation of agentic reinforcement learning for web automation. Decision stability is quantified by the sensitivity of future cost and failure outcomes to small perturbations in current actions. The learning objective encourages policies that operate in low-sensitivity regions of the decision space while optimizing task success under multiple cost budgets. The proposed approach is evaluated on 1,000–2,000 web tasks with injected UI and latency perturbations. Results show that stability-oriented policies produce smoother trajectories, lower variance in cost consumption, and improved robustness to execution noise compared with standard constrained RL baselines.
Cite
APA
Chen, E., O’Connor, L., & Thompson, S. (2026). Stability-Oriented Agentic Reinforcement Learning for Web Decision Systems under Cost and Failure Constraints. American Journal Of Big Data, 7(1), 202-211. https://doi.org/10.71465/ajbd3655
Vancouver
Chen E, O’Connor L, Thompson S. Stability-Oriented Agentic Reinforcement Learning for Web Decision Systems under Cost and Failure Constraints. American Journal Of Big Data. 2026;7(1):202-211. doi:10.71465/ajbd3655
BibTeX
@article{Chen2026,
author = {Chen, Emily and O’Connor, Liam and Thompson, Sarah},
title = {Stability-Oriented Agentic Reinforcement Learning for Web Decision Systems under Cost and Failure Constraints},
journal = {American Journal Of Big Data},
year = {2026},
volume = {7},
number = {1},
pages = {202--211},
doi = {10.71465/ajbd3655}
}
EUVIMED