Taming the exponential action set: Sublinear regret and fast convergence to nash equilibrium in online congestion games

J Dong, J Wu, S Wang, B Wang, W Chen - arXiv preprint arXiv:2306.13673, 2023 - arxiv.org
The congestion game is a powerful model that encompasses a range of engineering
systems such as traffic networks and resource allocation. It describes the behavior of a …

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games

J Dong, B Wang, Y Yu - International Conference on Artificial …, 2024 - proceedings.mlr.press
In this work, we study potential games and Markov potential games under stochastic cost
and bandit feedback. We propose a variant of the Frank-Wolfe algorithm with sufficient …

[PDF][PDF] Learning in concave games with imperfect information

P Mertikopoulos - arXiv preprint arXiv:1608.07310, 2016 - core.ac.uk
This paper examines the convergence properties of a class of learning schemes for concave
N-person games–that is, games with convex action spaces and individually concave payoff …