243 citations · 306 across the 9 of their papers we have counts for
23 papers
Boosting Offline Reinforcement Learning with Residual Generative Modeling
Hua Wei, Deheng Ye, Zhao Liu +5
Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) gen…
Learning to Route via Theory-Guided Residual Network
Chang Liu, Guanjie Zheng, Zhenhui Li
The heavy traffic and related issues have always been concerns for modern cities. With the help of deep learning and reinforcement learning, people have proposed various policies t…
Learning to Simulate on Sparse Trajectory Data
Hua Wei, Chacha Chen, Chang Liu +2
Simulation of the real-world traffic can be used to help validate the transportation policies. A good simulator means the simulated traffic is similar to real-world traffic, which…
Automatic Historical Feature Generation through Tree-based Method in Ads Prediction
Hongjian Wang, Qi Li, Lanbo Zhang +4
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads. In this paper, we study how to effici…
Online Structured Meta-learning
Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi +3
Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has s…
Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records
Jiatu Shi, Huaxiu Yao, Xian Wu +4
E-commerce business is revolutionizing our shopping experiences by providing convenient and straightforward services. One of the most fundamental problems is how to balance the dem…