The Lagging Anchor Algorithm: Reinforcement Learning in Two-Player Zero-Sum Games with Imperfect Information.

Fredrik A. Dahl

Published in: Mach. Learn. (2002)

Keyphrases

imperfect information
learning algorithm
reinforcement learning
computational complexity
perfect information
optimal solution

dynamic programming
matching algorithm
search space
np hard
upper bound

worst case
monte carlo
game theoretic
objective function
simulated annealing

path planning
game playing
single agent
game tree
multi agent