People who code: we want your input. Take the Survey

# Tag Info

That's exactly the point of the Policy Gradient Theorem. Let's go through he proof of this theorem - it relies on our ability to "loop" the reward expression $J(\theta,s)$, expressing it through $J(\theta,s')$ in the next state: $$J(\theta,s) = \mathbb{E}_{\tau\sim\pi_\theta}\left[ R(\tau) | s_0 = s\right]$$ \begin{align} J(\theta,s) & = \...