A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm

DOI10.1145/1842713.1842715zbMATH Open1490.62209OpenAlexW2029593259MaRDI QIDQ4635151FDOQ4635151

Authors: Sumit Kunnumkal, Huseyin Topaloglu 

Publication date: 16 April 2018

Published in: ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)

Full work available at URL: http://eprints.exchange.isb.edu/57/1/sup_projection.pdf

Recommendations

• Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm
• Asynchronous stochastic approximation and Q-learning
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing
• Stochastic approximation: Theory and applications
• Q-Learning with Linear Function Approximation

zbMATH Keywords

stochastic approximationQ-learningmax-norm projection

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20)

Cited In (2)

• Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing

This page was built for publication: A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4635151)