Regret of exploratory policy improvement and $q$-learning
This work addresses theoretical guarantees for reinforcement learning algorithms in continuous control settings, but appears incremental as it builds on prior methods.
The paper tackles the convergence of q-learning and exploratory policy improvement algorithms for controlled diffusion processes, providing quantitative error and regret analysis under specific model conditions.
We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J. Mach. Learn. Res., 24 (2023), 161) for controlled diffusion processes. Under suitable conditions on the growth and regularity of the model parameters, we provide a quantitative error and regret analysis of both the exploratory policy improvement algorithm and the $q$-learning algorithm.