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

作者：Chang Hyeong Soo^*; Hu Jiaqiao; Fu Michael C; Marcus Steven I

来源：IEEE Transactions on Automatic Control, 2010, 55(2): 463-468.

DOI：10.1109/TAC.2009.2036333

• Multi-armed bandit
• sample average approximation
• sampling
• two-person zero-sum Markov game (MG)

This technical note presents a recursive sampling-based algorithm for finite horizon two-person zero-sum Markov games (MGs) based on the Exp3 algorithm developed by Auer et al. for adaptive adversarial multi-armed bandit problems. We provide a finite-iteration bound to the equilibrium value of the induced "sample average approximation game" of a given MG and prove asymptotic convergence to the equilibrium value of the given MG. The time and space complexities of the algorithm are independent of the state space of the game.

• 出版日期2010-2