Skip to content
Sagan

Paper

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

Unreadunread

AI summary

arXiv:2606. 23995v1 Announce Type: new Abstract: Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games.