Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm

DOI10.1287/IJOC.1070.0240zbMATH Open1243.90235OpenAlexW2102195169MaRDI QIDQ2901012FDOQ2901012

Authors: Sumit Kunnumkal, Huseyin Topaloglu 

Publication date: 28 July 2012

Published in: INFORMS Journal on Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/ijoc.1070.0240

Recommendations

• Convergence of a Q-learning variant for continuous states and actions
• Q-Learning with Linear Function Approximation
• Asynchronous stochastic approximation and Q-learning
• \({\mathcal Q}\)-learning
• A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm

zbMATH Keywords

Markov decision processesQ-learningstochastic approximation methods

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited In (6)

• Shape constraints in economics and operations research
• A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm
• A Machine Learning–Enabled Partially Observable Markov Decision Process Framework for Early Sepsis Prediction
• Counterexample explanation by learning small strategies in Markov decision processes
• Q-learning for Markov decision processes with a satisfiability criterion
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing

This page was built for publication: Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2901012)