Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

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

Sign In

Full text access may be available.

To access full text, please use your member or institutional sign in.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)
Hyeong Soo Chang ; Dept. of Comput. Sci. & Eng., Sogang Univ., Seoul, South Korea ; Jiaqiao Hu ; Fu, M.C. ; Marcus, S.I.

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.

Published in:

Automatic Control, IEEE Transactions on  (Volume:55 ,  Issue: 2 )