1 code implementation • 3 May 2023 • Xiong-Hui Chen, Bowei He, Yang Yu, Qingyang Li, Zhiwei Qin, Wenjie Shang, Jieping Ye, Chen Ma
However, building a user simulator with no reality-gap, i. e., can predict user's feedback exactly, is unrealistic because the users' reaction patterns are complex and historical logs for each user are limited, which might mislead the simulator-based recommendation policy.
1 code implementation • NeurIPS 2021 • Xiong-Hui Chen, Yang Yu, Qingyang Li, Fan-Ming Luo, Zhiwei Qin, Wenjie Shang, Jieping Ye
Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline dataset, in order to ensure the robustness of the outcome policies.
no code implementations • 1 Jan 2021 • Xiong-Hui Chen, Yang Yu, Qingyang Li, Zhiwei Tony Qin, Wenjie Shang, Yiping Meng, Jieping Ye
Instead of increasing the fidelity of models for policy learning, we handle the distortion issue via learning to adapt to diverse simulators generated by the offline dataset.
no code implementations • 12 Jul 2019 • Wenjie Shang, Yang Yu, Qingyang Li, Zhiwei Qin, Yiping Meng, Jieping Ye
DEMER also derives a recommendation policy with a significantly improved performance in the test phase of the real application.