activity
20182022
most citedSample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation

16 citations · 48 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG202212 cited

Latent Hierarchical Causal Structure Discovery with Rank Constraints

Biwei Huang, Charles Jia Han Low, Feng Xie +2

Most causal discovery procedures assume that there are no latent confounders in the system, which is often violated in real-world problems. In this paper, we consider a challenging…

cs.LG20213 cited

FRITL: A Hybrid Method for Causal Discovery in the Presence of Latent Confounders

Wei Chen, Kun Zhang, Ruichu Cai +4

We consider the problem of estimating a particular type of linear non-Gaussian model. Without resorting to the overcomplete Independent Component Analysis (ICA), we show that under…

cs.LG202016 cited

Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation

Chaochao Lu, Biwei Huang, Ke Wang +3

Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios s…

cs.LG202010 cited

Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs

Feng Xie, Ruichu Cai, Biwei Huang +3

Causal discovery aims to recover causal structures or models underlying the observed data. Despite its success in certain domains, most existing methods focus on causal relations b…

cs.LG2020

Domain Adaptation as a Problem of Inference on Graphical Models

Kun Zhang, Mingming Gong, Petar Stojanov +3

This paper is concerned with data-driven unsupervised domain adaptation, where it is unknown in advance how the joint distribution changes across domains, i.e., what factors or mod…

cs.LG2019

Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

Biwei Huang, Kun Zhang, Mingming Gong +1

In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting t…