When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity
Stationarity rewards memory, but after a change the same history can mislead. We ask when forgetting should be permitted. E-process-authorized Thompson sampling (e-ATS) gives each arm full-history and discounted Beta states.
By Mayand Gulati, Kerong Wang, WeiChen AuarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 5, 2026.
Comments
Sign in to join the discussion.