From 3d043967505700fef295f1725c691f90ed8f754e Mon Sep 17 00:00:00 2001
From: Thomas Simonini <simonini.thomas.pro@gmail.com>
Date: Fri, 24 Feb 2023 14:17:33 +0100
Subject: [PATCH] Update language-models.mdx

---
 units/en/unitbonus3/language-models.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/units/en/unitbonus3/language-models.mdx b/units/en/unitbonus3/language-models.mdx
index db36cf7..0fffc19 100644
--- a/units/en/unitbonus3/language-models.mdx
+++ b/units/en/unitbonus3/language-models.mdx
@@ -20,7 +20,7 @@ There is therefore a potential synergy between LMs which can bring knowledge abo
 
 As a first attempt, the paper [“Grounding Large Language Models with Online Reinforcement Learning”](https://arxiv.org/abs/2302.02662v1) tackled the problem of **adapting or aligning a LM to a textual environment using PPO**. They showed that the knowledge encoded in the LM lead to a fast adaptation to the environment (opening avenue for sample efficiency RL agents) but also that such knowledge allowed the LM to better generalize to new tasks once aligned.
 
-<video src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit12/papier_v4.mp4" type="video/mp4" />
+<video src="https://huggingface.co/datasets/huggingface-deep-rl-course/course-images/resolve/main/en/unit12/papier_v4.mp4" type="video/mp4" controls />
 
 Another direction studied in [“Guiding Pretraining in Reinforcement Learning with Large Language Models”](https://arxiv.org/abs/2302.06692) was to keep the LM frozen but leverage its knowledge to **guide an RL agent’s exploration**. Such method allows the RL agent to be guided towards human-meaningful and plausibly useful behaviors without requiring a human in the loop during training.