Update website

docs/index.html

@@ -106,6 +106,7 @@ <h1 class="title is-1 publication-title"><span style="color: #e1144b;">Quality</
 					<div class="has-text-centered">Humanoid Hurdles 1</div>
 				</div>
 				<div class="item">
+					<div class="has-text-centered">Humanoid Hurdles 1</div>
 					<video poster="" autoplay controls muted loop playsinline height="100%">
 						<source src="./static/videos/walker2d_feet_contact_1.mp4" type="video/mp4">
 					</video>
@@ -176,10 +177,10 @@ <h2 class="subtitle has-text-centered">
 				<h2 class="title is-3">Abstract</h2>
 				<div class="content has-text-justified">
 					<p>
-						A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return only one solution specialized for a specific problem.
+						A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return <b>only one</b> solution specialized for a specific problem.
 					</p>
 					<p>
-						We introduce Quality-Diversity Actor-Critic (QDAC), an off-policy actor-critic deep reinforcement learning algorithm that leverages a value function critic and a successor features critic to learn high-performing and diverse behaviors. In this framework, the actor optimizes an objective that seamlessly unifies both critics using constrained optimization to (1) maximize return, while (2) executing diverse skills.
+						We introduce <span class="dnerf">Quality-Diversity Actor-Critic</span> (QDAC), an off-policy actor-critic deep reinforcement learning algorithm that leverages a <span style="color: #e1144b;">value function</span> critic and a <span style="color: #0053d6;">successor features</span> critic to learn high-performing and diverse behaviors. In this framework, the actor optimizes an objective that seamlessly unifies both critics using <b>constrained optimization</b> to (1) <span style="color: #e1144b;">maximize return</span>, while (2) <span style="color: #0053d6;">executing diverse skills</span>.
 					</p>
 					<p>
 						Compared with other Quality-Diversity methods, QDAC achieves significantly higher performance and more diverse behaviors on six challenging continuous control locomotion tasks. We also demonstrate that we can harness the learned skills to adapt better than other baselines to five perturbed environments. Finally, qualitative analyses showcase a range of remarkable behaviors.