Timezone: »

Symbolic Distillation for Learned TCP Congestion Control
S P Sharan · Wenqing Zheng · Kuo-Feng Hsu · Jiarong Xing · Ang Chen · Zhangyang Wang

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #336

Recent advances in TCP congestion control (CC) have achieved tremendous success with deep reinforcement learning (RL) approaches, which use feedforward neural networks (NN) to learn complex environment conditions and make better decisions. However, such ``black-box'' policies lack interpretability and reliability, and often, they need to operate outside the traditional TCP datapath due to the use of complex NNs. This paper proposes a novel two-stage solution to achieve the best of both worlds: first to train a deep RL agent, then distill its (over-)parameterized NN policy into white-box, light-weight rules in the form of symbolic expressions that are much easier to understand and to implement in constrained environments. At the core of our proposal is a novel symbolic branching algorithm that enables the rule to be aware of the context in terms of various network conditions, eventually converting the NN policy into a symbolic tree. The distilled symbolic rules preserve and often improve performance over state-of-the-art NN policies while being faster and simpler than a standard neural network. We validate the performance of our distilled symbolic rules on both simulation and emulation environments. Our code is available at https://github.com/VITA-Group/SymbolicPCC.

Author Information

S P Sharan (University of Texas at Austin)
S P Sharan

Ph.D. student of ECE (DICE) at @VITA-Group, The University of Texas at Austin, advised by Dr. Atlas Wang & Dr. Sandeep Chinchali

Wenqing Zheng (the University of Texas at Austin)
Kuo-Feng Hsu (Rice University)
Jiarong Xing (Microsoft)
Ang Chen (Rice University)
Zhangyang Wang (University of Texas at Austin)

More from the Same Authors