<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div class="" style="word-wrap:break-word"><span class="" style="font-size:14.666666984558105px">This is an announcement of Zhengxu Xia's MS Presentation</span><br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">===============================================</span><br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Candidate: Zhengxu Xia</span><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Date: Friday, April 15, 2022</span><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Time: 2 pm CST</span>
<div class=""><span class="" style="font-size:14.666666984558105px"><br class="">
</span></div>
<div class=""><span class="" style="font-size:14.666666984558105px">Location: JCL 390<br class="">
</span>
<div class=""><br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Remote Location: </span><a href="https://urldefense.com/v3/__https://uchicago.zoom.us/j/4302315616?pwd=ekoya3U3cFhNdFMxZTdLOCtRY1gyZz09__;!!BpyFHLRN4TMTrA!unUtGpHJrX-cAb12hx1ixSEGvvtsmIKLPpDxMVijVB4Tj6EqWWwVl93G7nUiOOLrES-SnS0P$" class="" style="font-size:14.666666984558105px">https://uchicago.zoom.us/j/4302315616?pwd=ekoya3U3cFhNdFMxZTdLOCtRY1gyZz09</a><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">M.S. Paper Title: Automatic Curriculum Generation for Learning Adaptation in Networking </span><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Abstract: As deep reinforcement learning (RL) showcases its strengths in networking and systems, its pitfalls also come to the public’s attention—when trained to handle a wide range of net- work workloads
and previously unseen deployment environments, RL policies often manifest suboptimal performance and poor generalizability.</span><br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">To tackle these problems, we present Genet, a new training framework for learning better RL-based network adaptation algorithms. Genet is built on the concept of curriculum learning, which has proved effective
against similar issues in other domains where RL is extensively employed. At a high level, curriculum learning gradually presents more difficult environments to the training, rather than choosing them randomly, so that the current RL model can make meaningful
progress in training. However, applying curriculum learning in networking is challenging because it remains unknown how to measure the “difficulty” of a network environment.</span><br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Instead of relying on handcrafted heuristics to determine the environment’s difficulty level, our insight is to utilize traditional rule-based (non-RL) baselines: If the current RL model performs significantly
worse in a network environment than the baselines, then the model’s potential to improve when further trained in this environment is substantial. There- fore, Genet automatically searches for the environments where the current model falls significantly behind
a traditional baseline scheme and iteratively promotes these environ- ments as the training progresses. Through evaluating Genet on three use cases—adaptive video streaming, congestion control, and load balancing, we show that Genet produces RL policies which
outperform both regularly trained RL policies and traditional baselines in each context, not only under synthetic workloads but also in real environments.</span><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Advisors: Junchen Jiang</span><br class="" style="font-size:14.666666984558105px">
<br class="" style="font-size:14.666666984558105px">
<span class="" style="font-size:14.666666984558105px">Committee Members: Junchen Jiang, Heather Zheng, and Francis Y. Yan</span>
<div class=""><span class="" style="font-size:14.666666984558105px"><br class="">
</span></div>
<div class=""><span class="" style="font-size:14.666666984558105px"></span></div>
</div>
</div>
</div>
<div class="" style="word-wrap:break-word">
<div class="">
<div class="">
<div class=""><span class="" style="font-size:14.666666984558105px"></span></div>
</div>
</div>
</div>
</body>
</html>