From 8641b05b09b6b77ffe0884cb344d144d551ec1fe Mon Sep 17 00:00:00 2001 From: Franz Srambical <79149449+emergenz@users.noreply.github.com> Date: Tue, 15 Nov 2022 15:00:03 +0100 Subject: [PATCH] Fix typo in documentation (#1177) --- docs/guide/checking_nan.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/guide/checking_nan.rst b/docs/guide/checking_nan.rst index 29f9e31..ef3762c 100644 --- a/docs/guide/checking_nan.rst +++ b/docs/guide/checking_nan.rst @@ -7,7 +7,7 @@ corrupted when a NaN or an inf is given or returned from the RL model. How and why? ------------ -The issue arises then NaNs or infs do not crash, but simply get propagated through the training, +The issue arises when NaNs or infs do not crash, but simply get propagated through the training, until all the floating point number converge to NaN or inf. This is in line with the `IEEE Standard for Floating-Point Arithmetic (IEEE 754) `_ standard, as it says: