🏢 CREST - FairPlay, ENSAE Paris
Local and Adaptive Mirror Descents in Extensive-Form Games
·321 words·2 mins·
loading
·
loading
Machine Learning
Reinforcement Learning
🏢 CREST - FairPlay, ENSAE Paris
LocalOMD: Adaptive OMD in extensive-form games achieves near-optimal sample complexity by using fixed sampling and local updates, reducing variance and generalizing well.