Gradient-free online learning in games with delayed rewardsAm lie H liouPanayotis Mertikopouloset al.2020ICML 2020
Finite-Time last-iterate convergence for multi-agent learning in gamesTianyi LinZhengyuan Zhouet al.2020ICML 2020
On the convergence of mirror descent beyond stochastic convex programmingZhengyuan ZhouPanayotis Mertikopouloset al.2020SIOPT