Q-learning for Markov decision processes with a satisfiability criterion

DOI10.1016/J.SYSCONLE.2018.01.003MaRDI QIDQ1749413zbMATH OpenOpenAlexFDO

Authors Suhail M. Shah, Vivek Borkar

Publication date 16 May 2018

Published in Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.sysconle.2018.01.003

zbMATH Keywords

differential inclusionsMarkov decision processesreplicator dynamicssatisfiabilityQ-learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03)

Recommendations

• Exploiting the structural properties of the underlying Markov decision problem in the Q-learning algorithm
• Q-learning for distributionally robust Markov decision processes
• Learning algorithms for finite horizon constrained Markov decision processes
• Learning algorithms for Markov decision processes
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Q-learning and enhanced policy iteration in discounted dynamic programming
• \({\mathcal Q}\)-learning
• Reinforcement learning in robust Markov decision processes

Cites work

• scientific article; zbMATH DE number 5869530 (Why is no real title available?)
• scientific article; zbMATH DE number 3855514 (Why is no real title available?)
• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• An analog of the minimax theorem for vector payoffs
• Approachability in Stackelberg stochastic games with vector costs
• Approachable sets of vector payoffs in stochastic games
• Asynchronous Stochastic Approximations
• Asynchronous stochastic approximation with differential inclusions
• Dynamical systems and variational inequalities
• Estimation and control in discounted stochastic dynamic programming
• Evolutionary Games and Population Dynamics
• Guaranteed performance regions in Markovian systems with competing decision makers
• Learning algorithms for Markov decision processes with average cost
• Multiplicative updates outperform generic no-regret learning in congestion games (extended abstract)
• Stochastic Approximations and Differential Inclusions
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• Stochastic approximation with two time scales
• Structural Properties of Optimal Transmission Policies Over a Randomly Varying Channel
• Survey of Measurable Selection Theorems
• The Borkar-Meyn theorem for asynchronous stochastic approximations
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• The multiplicative weights update method: a meta-algorithm and applications
• The projection dynamic and the geometry of population games

Cited in

(5)

• \(L^\ast\)-based learning of Markov decision processes (extended version)
• scientific article; zbMATH DE number 5670432 (Why is no real title available?)
• Prospect-theoretic Q-learning
• Revisiting SIR in the age of COVID-19: explicit solutions and control problems
• Counterexample explanation by learning small strategies in Markov decision processes

This page was built for publication: Q-learning for Markov decision processes with a satisfiability criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1749413)