From fd9424c243ff1a0e6d32c09ed0236d443ec32c39 Mon Sep 17 00:00:00 2001 From: earnesdm Date: Sun, 25 Aug 2024 13:41:45 -0400 Subject: [PATCH] Fix a broken link. --- docs/spinningup/rl_intro3.rst | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/docs/spinningup/rl_intro3.rst b/docs/spinningup/rl_intro3.rst index 34e4d5d57..57c64e423 100644 --- a/docs/spinningup/rl_intro3.rst +++ b/docs/spinningup/rl_intro3.rst @@ -338,9 +338,7 @@ is called the **reward-to-go** from that point, and this policy gradient express **But how is this better?** A key problem with policy gradients is how many sample trajectories are needed to get a low-variance sample estimate for them. The formula we started with included terms for reinforcing actions proportional to past rewards, all of which had zero mean, but nonzero variance: as a result, they would just add noise to sample estimates of the policy gradient. By removing them, we reduce the number of sample trajectories needed. -An (optional) proof of this claim can be found `here`_, and it ultimately depends on the EGLP lemma. - -.. _`here`: ../spinningup/extra_pg_proof1.html +An (optional) proof of this claim can be found `here <../spinningup/extra_pg_proof1.html>`_, and it ultimately depends on the EGLP lemma. Implementing Reward-to-Go Policy Gradient =========================================