Eqs. (A 4)–(A 7) — the infinite-step return is $V(n) \approx Gn + W$ with $G = \pi\rho$ and Cesàro bias $W = (Z-\Pi)\rho + \Pi V(0)$

Initializing...

Eqs. (A 4)–(A 7) — the infinite-step return is $V(n) \approx Gn + W$ with $G = \pi\rho$ and Cesàro bias $W = (Z-\Pi)\rho + \Pi V(0)$ · Prove2Me