Under a uniformly bounded second moment for local token advantages, the paper proves a remaining-horizon-squared upper bound for undiscounted sequence credit and a horizon-independent upper bound for fixed γ<1. · CiteArk
Under a uniformly bounded second moment for local token advantages, the paper proves a remaining-horizon-squared upper bound for undiscounted sequence credit and a horizon-independent upper bound for fixed γ<1.
来源：paper:PDF p. 5, Theorem 3.3; proof on PDF p. 15
