<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 14pt; color: rgb(0, 0, 0);">
<b><i>"Multi-Agent Reinforcement Learning-Based Routing for Dragonfly Networks"</i></b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 14pt; color: rgb(0, 0, 0);" class="elementToProof">
<b><br>
</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 14pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>Xin Yuan</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Department of Computer Science</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Florida State University (FSU) </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Please feel free to forward/share this invitation with other groups/disciplines that might be interested in this talk/topic. All are welcome to attend. </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
NOTE: In-person attendance is requested in our 499 Dirac Science Library (DSL) Seminar Room. Zoom access is intended for external (non-departmental) participants only. </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>https://fsu.zoom.us/j/94273595552 </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Meeting # <b>942 7359 5552 </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
🎦 Colloquium recordings will be made available here, <a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fcolloquium&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7C601d74a6c5fd46c8baf908de89f4bcc2%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C639099881384912762%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=zbEhGJ%2BO0gKeeCM9JXC4qTA4FUDK4ZXRhfJ%2FGQQBVyk%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/colloquium">
https://www.sc.fsu.edu/colloquium</a> </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b><br>
</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>Wednesday, Mar 25, 2026, Schedule: </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
* 3:00 to 3:30 PM Eastern Time (US and Canada) </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
☕ Nespresso & Teatime - 417 DSL Commons </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>* 3:30 to 4:30 PM Eastern Time (US and Canada) </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>🕟 Colloquium - 499 DSL Seminar Room </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<b>Abstract: </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Reinforcement Learning (MARL)-based routing has emerged as a promising approach for high-performance interconnect networks such as Dragonfly, offering a viable alternative to the widely used Universal Globally Adaptive Load-balanced (UGAL) routing. Practical
routing on modern interconnects must satisfy various requirements, such as being deadlock-free and having a limited path length. These requirements impose routing constraints, which in turn pose challenges for MARL-based routing. In particular, two important
issues must be addressed for a MARL-based scheme to be effective. First, in the presence of routing constraints, sufficient path diversity to accommodate different traffic conditions is essential. Second, since routing constraints influence how Q-values are
propagated in a MARL-based scheme, it is vital that the value propagation mechanism accounts for the routing constraints. Existing MARL-based routing schemes for Dragonfly fall short in addressing both issues. As a result, while they achieve high performance
for some traffic conditions, they may exhibit poor performance or even pathological behaviors in other scenarios. In this work, we discuss the limitations of existing MARL-based routing schemes for Dragonfly, present methods to address the two key issues,
and develop UGAL-Q, a novel MARL-based scheme that resolves these issues and overcomes the problems in existing approaches. We perform extensive evaluations using both synthetic traffic and HPC application benchmarks. The results demonstrate that our scheme
is more effective than existing ones and is a robust routing solution for Dragonfly.</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Additional colloquium details can be found here.</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fnews-and-events%2Fcolloquium%2F1914-colloquium-with-xin-yuan-2026-03-25&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7C601d74a6c5fd46c8baf908de89f4bcc2%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C639099881384960575%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=UOBCBA2%2B7E8Erg4ydERUdC5GWHAc1zSJV5SwytuN3N4%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/news-and-events/colloquium/1914-colloquium-with-xin-yuan-2026-03-25">https://www.sc.fsu.edu/news-and-events/colloquium/1914-colloquium-with-xin-yuan-2026-03-25</a></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
</body>
</html>