<ul><li>Researchers propose efficient learning algorithms for entropy-regularized Markov Decision Processes (MDPs) with large or continuous state and action spaces.</li><li>The algorithms integrate fixed-point iteration with multilevel Monte Carlo techniques and a stochastic approximation of the Bellman operator.</li><li>Using a biased plain Monte Carlo estimate for the Bellman operator leads to quasi-polynomial sample complexity, while an unbiased randomized multilevel approximation achieves polynomial sample complexity in expectation.</li><li>The proposed algorithms demonstrate performance guarantees independent of the dimensions or sizes of state and action spaces.</li></ul>

Efficient Learning for Entropy-regularized Markov Decision Processes via Multilevel Monte Carlo

Discover more