Improving reinforcement learning algorithms: Towards optimal learning rate policies

DOI10.1111/mafi.12378arXiv1911.02319OpenAlexW2989340622MaRDI QIDQ6196297

Othmane Mounjid, Charles-Albert Lehalle

Publication date: 14 March 2024

Published in: Mathematical Finance (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.02319

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Financial markets (91G15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic approximation methods for constrained and unconstrained systems
• Mean field game of controls and an application to trade crowding
• Relative deviation learning bounds and generalization with unbounded loss functions
• Optimal aggregation of classifiers in statistical learning.
• DGM: a deep learning algorithm for solving partial differential equations
• Proximal Splitting Methods in Signal Processing
• Functional Approximations and Dynamic Programming
• Learning a functional control for high-frequency finance
• Deep Reinforcement Learning for Market Making in Corporate Bonds: Beating the Curse of Dimensionality
• A New Conjugate Gradient Method with Guaranteed Descent and an Efficient Line Search
• Advanced Lectures on Machine Learning
• Asymptotic Distribution of Stochastic Approximation Procedures
• Convexity, Classification, and Risk Bounds
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one

This page was built for publication: Improving reinforcement learning algorithms: Towards optimal learning rate policies