Regret minimization in repeated matrix games with variable stage duration.

Shie Mannor Nahum Shimkin

Published in: Games Econ. Behav. (2008)

Keyphrases

regret minimization
nash equilibrium
game theoretic
game theory
continuous time markov process
multi agent learning
nash equilibria
singular value decomposition
linear algebra
domain knowledge
lower bound
low rank
serious games
imperfect information