Duohan Zhang — accepted AI-conference papers

2024

Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning

Hadi Hosseini, Sanjukta Roy, Duohan Zhang

NeurIPS 2024poster

Two-sided matching markets describe a large class of problems wherein participants from one side of the market must be matched to those from the other side according to their preferences. In many real-world applications (e.g. content matching or online labor markets), the knowledge about preferences…

Cited by 3 Source ↗PDF ↗Scholar ↗

2022

Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning

Rujie Zhong, Duohan Zhang, Lukas Schäfer, Stefano V Albrecht, Josiah P. Hanna

NeurIPS 2022accept

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle distinction between on-policy data and on-policy sampling in the c…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗