I am following the OpenAI's spinning up tutorial Part 3: Intro to Policy Optimization. It is mentioned there that the reward-to-go reduces the variance of the policy gradient. While I understand the intuition behind it, I struggle to find a proof in the literature.
-
1$\begingroup$ Does the answer to this question answer yours as well? $\endgroup$– user5093249Jun 10, 2020 at 13:55
-
$\begingroup$ No, the linked question only proofs that the reward-to-go does not introduce any bias to the gradient estimate. $\endgroup$– sirKris van DelaJun 10, 2020 at 14:14
-
$\begingroup$ This is nontrivial to prove, actually anything involving stochastic function approximation is nontrivial. You can search research papers, you won't find it in any book right now $\endgroup$– FourierFluxJun 10, 2020 at 14:33