Can I read Gaussian Approximation For Asynchronous Q-Learning: A. Rubtsov, S. Samsonov, V. Ulyanov, A. Naumov April 9, 2026 on EtoBox?

Gaussian Approximation For Asynchronous Q-Learning: A. Rubtsov, S. Samsonov, V. Ulyanov, A. Naumov April 9, 2026 by 06- Chí Bảo Lê is a document available to read on EtoBox.

What is Gaussian Approximation For Asynchronous Q-Learning: A. Rubtsov, S. Samsonov, V. Ulyanov, A. Naumov April 9, 2026 about?

This paper presents a Gaussian approximation for the Polyak–Ruppert averaged iterates of the asynchronous Q-learning algorithm, establishing a convergence rate of n−1/6 log4(nSA) under specific conditions. The authors derive a high-dimensional central limit theorem for sums of martingale differences, which is significant for understanding the behavior of the algorithm. Additionally, they provide bounds for high-order moments of the algorithm

Author

06- Chí Bảo Lê

Language

EN