English

Data-Driven Knowledge Transfer in Batch $Q^*$ Learning

Machine Learning 2026-01-13 v3 Methodology Machine Learning

Abstract

In data-driven decision-making in marketing, healthcare, and education, it is desirable to utilize a large amount of data from existing ventures to navigate high-dimensional feature spaces and address data scarcity in new ventures. We explore knowledge transfer in dynamic decision-making by concentrating on batch stationary environments and formally defining task discrepancies through the lens of Markov decision processes (MDPs). We propose a framework of Transferred Fitted QQ-Iteration algorithm with general function approximation, enabling the direct estimation of the optimal action-state function QQ^* using both target and source data. We establish the relationship between statistical performance and MDP task discrepancy under sieve approximation, shedding light on the impact of source and target sample sizes and task discrepancy on the effectiveness of knowledge transfer. We show that the final learning error of the QQ^* function is significantly improved from the single task rate both theoretically and empirically.

Keywords

Cite

@article{arxiv.2404.15209,
  title  = {Data-Driven Knowledge Transfer in Batch $Q^*$ Learning},
  author = {Elynn Chen and Xi Chen and Wenbo Jing},
  journal= {arXiv preprint arXiv:2404.15209},
  year   = {2026}
}
R2 v1 2026-06-28T16:04:00.996Z