Work

Non-Stationary Representation Learning in Sequential Linear Bandits

Year: 2022

Type: article

Abstract: In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from different environments. The embeddings of tasks in each environment share a low-dimensional feature extractor calledrepresentation, and representations are different across environments. We propose an online algorithm that facilitates efficient decision-making by learning and transferring non-stationary representations in an adaptive fashion. We prove that our algorithm significantly outperforms the existing ones that treat tasks independently. We also conduct experiments using both synthetic and real data to validate our theoretical insights and demonstrate the efficacy of our algorithm.

Source: IEEE Open Journal of Control Systems

DOI: 10.1109/ojcsys.2022.3178540

Authors: Yuzhen Qin, Tommaso Menara, Samet Oymak, ShiNung Ching, Fabio Pasqualetti

Institutions: University of California, Riverside, University of California San Diego, Washington University in St. Louis

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: gold

Estimated APC paid: $1,850

Funders: Air Force Office of Scientific Research, Army Research Office