Trang chủ / Tin tức / Khoa học & công nghệ
Khoa học & công nghệ

BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets

09/11/2026 · Thành viên: PGS.TS Bùi Xuân Thành · Nguồn: OpenAlex

Constrained preference-conditioned MORL typically assumes full task observability, treating preferences and safety budgets as stationary task signals. In real-world deployment, however, these signa...

<p><strong>Tác giả:</strong> Bui Trong Duc, Huynh Thi Thanh Binh</p>

<p>Constrained preference-conditioned MORL typically assumes full task observability, treating preferences and safety budgets as stationary task signals. In real-world deployment, however, these signals are often unreliable proxies: intent may drift, safety tolerances may shift with context, and exposed descriptors may be noisy, delayed, or incomplete. We therefore formulate constrained preference-conditioned MORL as a partially observed task-specification problem, where the agent must navigate...</p>

<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.48550/arxiv.2611.12053" target="_blank" rel="noopener">https://doi.org/10.48550/arxiv.2611.12053</a></p>

<p>📖 <a href="https://doi.org/https://doi.org/10.48550/arxiv.2611.12053" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>

Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex