$Q$-Learning in a Stochastic Stackelberg Game between an Uninformed Leader and a Naive Follower

DOI10.1137/S0040585X97T989386zbMath1485.91034OpenAlexW2942727117MaRDI QIDQ5380530

Dmitry B. Rokhlin

Publication date: 5 June 2019

Published in: Theory of Probability & Its Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0040585x97t989386

zbMATH Keywords

Boltzmann distributiondiscounted criterionstochastic Stackelberg gameleader\(Q\)-learningfollower

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Stochastic games, stochastic differential games (91A15) Rationality and learning in game theory (91A26)

Cites Work

• Unnamed Item
• Unnamed Item
• Sequential Stackelberg equilibria in two-person games
• Asynchronous stochastic approximation and Q-learning
• Multiagent learning using a variable learning rate
• Boundedness of iterates in \(Q\)-learning
• Martingales and stochastic integrals. I

This page was built for publication: $Q$-Learning in a Stochastic Stackelberg Game between an Uninformed Leader and a Naive Follower