We study convergence properties of distributed learning dynamics in repeated stochastic
routing games. The game is stochastic in that each player observes a stochastic vector, the
conditional expectation of which is equal to the true loss (almost surely). In particular, we
propose a model in which every player m follows a stochastic mirror descent dynamics with
Bregman divergence D ψm and learning rates η tm= θ m t-αm. We prove that if all players
use the same sequence of learning rates, then their joint strategy converges almost surely to …