From 2e49a1fb6faaad090716a795b16b33ea982f84f8 Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Wed, 4 Jan 2023 11:14:36 +0100 Subject: [PATCH] Update quiz.mdx --- units/en/unit4/quiz.mdx | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/units/en/unit4/quiz.mdx b/units/en/unit4/quiz.mdx index 13d9047..c509b4e 100644 --- a/units/en/unit4/quiz.mdx +++ b/units/en/unit4/quiz.mdx @@ -10,12 +10,12 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour { text: "Policy-gradient methods can learn a stochastic policy", explain: "", - correct: true + correct: true, }, { text: "Policy-gradient methods are more effective in high-dimensional action spaces and continuous actions spaces", explain: "", - correct: true + correct: true, }, { text: "Policy-gradient converges most of the time on a global maximum.", @@ -53,12 +53,12 @@ The best way to learn and [to avoid the illusion of competence](https://www.cour text: "In Policy-based methods, we can optimize the parameter θ **indirectly** by maximizing the local approximation of the objective function with techniques like hill climbing, simulated annealing, or evolution strategies.", explain: "", correct: true, - } - { - text: "In Policy-gradient methods, we optimize the parameter θ **directly** by performing the gradient ascent on the performance of the objective function.", - explain: "", - correct: true - }, + }, + { + text: "In Policy-gradient methods, we optimize the parameter θ **directly** by performing the gradient ascent on the performance of the objective function.", + explain: "", + correct: true, + }, ]} />