Exponentially fast convergence to (strict) equilibrium via hedging

Motivated by applications to data networks where fast convergence is essential, we analyze the problem of learning in generic N-person games that admit a Nash equilibrium in pure strategies. Specifically, we consider a scenario where players interact repeatedly and try to learn from past experience by small adjustments based on local – and possibly imperfect – payoff information. For concreteness, we focus on the so-called “hedge” variant of the exponential weights (EW) algorithm where players select an action with probability proportional to the exponential of the action’s cumulative payoff over time. When the players have perfect information on their mixed payoffs, the algorithm converges locally to a strict equilibrium and the rate of convergence is exponentially fast – of the order of O(exp(−a ∑t j=1 γj)) where a > 0 is a constant and γj is the algorithm’s step-size. In the presence of uncertainty, convergence requires a more conservative step-size policy, but with high probability, the algorithm still achieves an exponential convergence rate.