Jul 1 – 5, 2024
Institut de Mathématiques de Toulouse
Europe/Paris timezone

Regret based learning algorithms have found applications in various environments including stochastic, adversarial and multi-agent ones. While optimal convergence rates were known in the stochastic and adversarial settings, the corresponding results in the multi-agent settings have started to appear only recently. 

The aim of this workshop is to showcase recent trends and advances in regret-based learning algorithms in multi-agent competitive environments.

Institut de Mathématiques de Toulouse
Amphithéâtre Schwartz
Université Paul Sabatier Toulouse 3 118 route de Narbonne, Toulouse Bâtiment 1R3
Go to map