57 citations
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022★ 18 cited
Lexicographic Multi-Objective Reinforcement Learning
Joar Skalse, Lewis Hammond, Charlie Griffin +1
In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. These are problems that involve multiple reward signals, and where t…
cs.LG2022★ 10 cited
End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation
Shiyu Wang, Fan Zhou, Yinbo Sun +3
Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconc…
cs.LG2022★ 44 cited
Automatic Expert Selection for Multi-Scenario and Multi-Task Search
Xinyu Zou, Zhi Hu, Yiming Zhao +4
Multi-scenario learning (MSL) enables a service provider to cater for users' fine-grained demands by separating services for different user sectors, e.g., by user's geographical re…