Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games

DOI10.1109/TAC.2009.2036333zbMath1368.91022MaRDI QIDQ4978716

Steven I. Marcus, Jiaqiao Hu, Michael C. Fu, Hyeong Soo Chang

Publication date: 25 August 2017

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Mathematics Subject Classification ID

2-person games (91A05) Stochastic games, stochastic differential games (91A15)

Related Items (2)

Approximation of zero-sum continuous-time Markov games under the discounted payoff criterion ⋮ An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games

This page was built for publication: Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games