A Discrete-Time Switching System Analysis of Q-Learning

DOI10.1137/22m1489976arXiv2102.08583MaRDI QIDQ6107867

Niao He, Dong Hwan Lee, Jianghai Hu

Publication date: 28 June 2023

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.08583

zbMATH Keywords

stochastic approximationQ-learningswitched linear system

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Graph theory (including graph drawing) in computer science (68R10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asynchronous stochastic approximation and Q-learning
• \({\mathcal Q}\)-learning
• Error bounds for constant step-size \(Q\)-learning
• Boundedness of iterates in \(Q\)-learning
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• ${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Stability and Stabilizability of Switched Linear Systems: A Survey of Recent Results
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction