Update index.html

Author: panmt

index.html

@@ -110,7 +110,7 @@ <h2 class="title is-3">Abstract</h2>
                     However, it struggles with suboptimal offline behaviors and inaccurate value estimation due to the lack of environmental interaction. 
                     We present <b>Video-Enhanced Offline RL (VeoRL)</b>, a model-based method that constructs an interactive world model from diverse, unlabeled video data readily available online. 
                     Leveraging model-based behavior guidance, our approach transfers commonsense knowledge of control policy and physical dynamics from natural videos to the RL agent within the target domain. 
-                    VeoRL achieves substantial performance gains (over <span class="math">100<span class="math-percent">%</span></span> in some cases) across visual control tasks in robotic manipulation, autonomous driving, and open-world video games.
+                    VeoRL achieves substantial performance gains (over <span style="font-style: italic; font-family: Times New Roman;">100%</span> in some cases) across visual control tasks in robotic manipulation, autonomous driving, and open-world video games.
                     </p>
                 </div>
             </div>