Song Ju

2 accepted papers

2024

Off-Policy Selection for Initiating Human-Centric Experimental Design

Ge Gao, Xi Yang, Qitong Gao, Song Ju, Miroslav Pajic, Min Chi

NeurIPS 2024poster

In human-centric applications like healthcare and education, the \textit{heterogeneity} among patients and students necessitates personalized treatments and instructional interventions. While reinforcement learning (RL) has been utilized in those tasks, off-policy selection (OPS) is pivotal to close…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

On Trajectory Augmentations for Off-Policy Evaluation

Ge Gao, Qitong Gao, Xi Yang, Song Ju, Miroslav Pajic, Min Chi

ICLR 2024poster

In the realm of reinforcement learning (RL), off-policy evaluation (OPE) holds a pivotal position, especially in high-stake human-involved scenarios such as e-learning and healthcare. Applying OPE to these domains is often challenging with scarce and underrepresentative offline training trajectories…

Cited by 4 Source ↗PDF ↗Scholar ↗