الباحثون

Yuexing Li

المنشورات 2

نسخة أولية وصول مفتوح

Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation

Biao Xiang, Ali Eshragh, Yuexing Li وآخرون · 2026

Off-policy evaluation (OPE) estimates the value of a target policy from logged data, but limited behavior-policy coverage can force high-variance reweighting or reward-model extrapolation. Counterfactual annotations can add evidence about unobserved actions, yet practical sources, including domain experts and large lan …

نسخة أولية وصول مفتوح

Decision-Focused Learning in MDPs: An Occupancy Measure Approach

Zihao Zhao, Ashwath K. Karunakaram, Ali Eshragh وآخرون · 2026

In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT conditions of the Bellman equation and require solving a linear system over all state-action pairs, limiting its scalability. We address this by reformulating the MDP as an …

المؤلفون المشاركون