Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments

WB Du, T Qin, TZ Wang, ZH Zhou - The Thirty-eighth Annual …, 2024 - openreview.net
Machine learning (ML) has achieved remarkable success in prediction tasks. In many real-
world scenarios, rather than solely predicting an outcome using an ML model, the crucial …

Policy-conditioned Environment Models are More Generalizable

R Chen, XH Chen, Y Sun, S **ao, M Li, Y Yu - Forty-first International … - openreview.net
In reinforcement learning, it is crucial to have an accurate environment dynamics model to
evaluate different policies' value in downstream tasks like offline policy optimization and …

[PDF][PDF] Gradient-Based Nonlinear Rehearsal Learning with Multivariate Alterations

T Qin, TZ Wang, ZH Zhou - 2025 - lamda.nju.edu.cn
Abstract Machine learning (ML) has made significant advancements across various
domains, with a shifting focus from purely predictive tasks to decision-making. The recent …

An Efficient Maximal Ancestral Graph Listing Algorithm

TZ Wang, WB Du, ZH Zhou - Forty-first International Conference on … - openreview.net
Maximal ancestral graph (MAG) is a prevalent graphical model to characterize causal
relations in the presence of\emph {latent variables} including latent confounders and …