From 9ae8ffff24064acc5e8f696c9ffb271e6f0dcb8c Mon Sep 17 00:00:00 2001 From: Nhan Nguyen <35358825+hiimnhan@users.noreply.github.com> Date: Fri, 11 Jul 2025 10:41:42 +0700 Subject: [PATCH] Update pg-theorem.mdx log function transform wrong typo it should be P(\tau;\theta) instead of P(\tau|\theta --- units/en/unit4/pg-theorem.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/units/en/unit4/pg-theorem.mdx b/units/en/unit4/pg-theorem.mdx index ff619136..566d36cb 100644 --- a/units/en/unit4/pg-theorem.mdx +++ b/units/en/unit4/pg-theorem.mdx @@ -36,7 +36,7 @@ Thus we can rewrite the sum as We can then use the *derivative log trick* (also called *likelihood ratio trick* or *REINFORCE trick*), a simple rule in calculus that implies that \\( \nabla_x log f(x) = \frac{\nabla_x f(x)}{f(x)} \\) -So given we have \\(\frac{\nabla_\theta P(\tau;\theta)}{P(\tau;\theta)} \\) we transform it as \\(\nabla_\theta log P(\tau|\theta) \\) +So given we have \\(\frac{\nabla_\theta P(\tau;\theta)}{P(\tau;\theta)} \\) we transform it as \\(\nabla_\theta log P(\tau;\theta) \\)