@@ -135,7 +135,7 @@ <h2 class="title is-3 has-text-centered section-heading">Abstract</h2>
   <div class="container is-max-desktop">
     <h2 class="title is-3 has-text-centered section-heading">Setting</h2>
     <div class="callout-new content is-size-5">
-      <p class="mb-0"><strong><a href="https://arxiv.org/abs/2207.04136" target="_blank">CompoSuite</a></strong> (Mendez et al., 2022) provides <strong>4×4×4×4 = 256 tasks</strong> by composing one element from each axis: robot, object, obstacle, and objective. Our main experiments study a <strong>14-task training regime</strong> where the robot is fixed to IIWA (the remaining three axes vary), providing access to 4×4×4 = 64 possible task combinations. We evaluate our approach on 32 tasks that are not used during training.</p>
+      <p class="mb-0">To ground this idea, we use <strong><a href="https://arxiv.org/abs/2207.04136" target="_blank">CompoSuite</a></strong> (Mendez et al., 2022), which provides <strong>4×4×4×4 = 256 tasks</strong> by composing one element from each axis: robot, object, obstacle, and objective. Our main experiments study a <strong>14-task training regime</strong> where the robot is fixed to IIWA (the remaining three axes vary), providing access to 4×4×4 = 64 possible task combinations. We evaluate our approach on 32 tasks that are not used during training.</p>
     </div>
     <div class="compo-grid">
       <figure class="has-text-centered">
@@ -238,7 +238,7 @@ <h2 class="title is-3 has-text-centered section-heading">Environment interaction
     <div class="callout-new content is-size-5">
       <p class="mb-2">Iterative compositional generation still needs <strong>simulator rollouts</strong> to score candidate policies - but those steps only <strong>evaluate datasets</strong>, they do not imitate data collection or online learning.</p>
       <p class="mb-0">We compare to <strong><a href="https://arxiv.org/abs/2302.02948" target="_blank">RLPD</a></strong> (Ball et al., 2023) (offline + online RL) starting from the same 14-task expert pool, allowing up to <strong>100k</strong> on-policy steps per held-out task. Our method reaches much higher success and return with only <strong>~20k</strong> evaluation interactions per task after four refinement rounds - demonstrating that a small amount of structured evaluation can validate massive parallel synthetic rollouts (~1M model-generated transitions per task).</p>
-      <p class="mt-3 mb-0">Note that <strong>our approach is not tied to this particular choice of data evaluation and any suitable scoring function that assesses the utility of generated data could be used instead</strong>.</p>
+      <p class="mt-3 mb-0">Note that <strong>our approach is not tied to this particular choice of data evaluation</strong> and <strong>any suitable scoring function that assesses the utility of generated data could be used instead</strong>.</p>
     </div>
 
     <figure class="pdf-figure">