New algorithms of the Q-learning type

DOI10.1016/J.AUTOMATICA.2007.09.009MaRDI QIDQ2440701zbMATH OpenOpenAlexFDO

Authors Shalabh Bhatnagar, K. Mohan Babu

Publication date 19 March 2014

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2007.09.009

zbMATH Keywords

Markov decision processesQ-learningreinforcement learningSPSAtwo-timescale stochastic approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic learning and adaptive control (93E35)

Recommendations

• \({\mathcal Q}\)-learning
• Multiscale Q-learning with linear function approximation
• Asynchronous stochastic approximation and Q-learning
• Q-learning and policy iteration algorithms for stochastic shortest path problems
• Q-Learning for Risk-Sensitive Control

Cites work

• \({\mathcal Q}\)-learning
• A one-measurement form of simultaneous perturbation stochastic approximation
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Asynchronous stochastic approximation and Q-learning
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Stochastic approximation with two time scales
• Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences

Cited in

(13)

• Fast online \(Q(\lambda)\)
• \({\mathcal Q}\)-learning
• Approximate stochastic annealing for online control of infinite horizon Markov decision processes
• A constrained optimization perspective on actor-critic algorithms and application to network routing
• A study on a Q-learning algorithm based on ART 2
• Multiscale Q-learning with linear function approximation
• scientific article; zbMATH DE number 1804127 (Why is no real title available?)
• Q-learning and policy iteration algorithms for stochastic shortest path problems
• A Q-learning and TD error based task scheduling algorithm for sensor nodes
• scientific article; zbMATH DE number 1881096 (Why is no real title available?)
• Simulation research of the applicability of Q-learning algorithm in CSPS systems with non-Poisson part flow
• A Q-learning algorithm for Markov decision processes with continuous state spaces
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing

This page was built for publication: New algorithms of the Q-learning type

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2440701)