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

arXiv: https://arxiv.org/abs/2404.15209 · HTML: https://mlsanity.com/paper/2404.15209/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2024.

## Built on by (most cited first, 4 of 4)

- [Tensor-Fused Multi-View Graph Contrastive Learning](https://mlsanity.com/paper/2410.15247/) (2024)
- [Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift](https://mlsanity.com/paper/2505.17203/) (2025)
- [One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL](https://mlsanity.com/paper/2601.21924/) (2026)
- [Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints](https://mlsanity.com/paper/2605.19140/) (2026)

## Abstract (arXiv)

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 Q-Iteration algorithm with general function approximation, enabling the direct estimation of the optimal action-state function Q^* 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 Q^* function is significantly improved from the single task rate both theoretically and empirically.