Nonlinear two-player zero-sum game approximate solution using a Policy Iteration algorithm.

Marcus Johnson Shubhendu Bhasin Warren E. Dixon

Published in: CDC/ECC (2011)

Keyphrases

game theory
policy iteration algorithm
game playing
markov decision processes
nash equilibrium
cooperative
finite state
imperfect information
reinforcement learning
np hard
dynamic programming
policy iteration
stochastic games