Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, Q-learning has proven to be a powerful algorithm in model-free settings. However, the extension of Q-learning to a model-based framework remains relatively unexplored. In this paper, we investigate the sample complexity of Q-learning when integrated with a model-based approach. The proposed algorihtms learns both the model and Q-value in an online manner. We demonstrate a near-optimal sample complexity result within a broad range of step sizes.
@article{arxiv.2402.11877,
title = {Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ},
author = {Han-Dong Lim and HyeAnn Lee and Donghwan Lee},
journal= {arXiv preprint arXiv:2402.11877},
year = {2026}
}