Claim 1 says there exists some uy value for which the algorithm gets high regret, so we might as well assume it’s chosen to maximize regret.
Claim 2 says the algorithm has low regret regrardless of uy , so we might as well assume it’s chosen to maximize regret.
Claim 1 says there exists some uy value for which the algorithm gets high regret, so we might as well assume it’s chosen to maximize regret.
Claim 2 says the algorithm has low regret regrardless of uy , so we might as well assume it’s chosen to maximize regret.