AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Symbolic Distillation for Learned TCP Congestion Control

S P Sharan, Wenqing Zheng, Kuo-Feng Hsu, Jiarong Xing, Ang Chen, Zhangyang Wang

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add context-specific branches and a branch decider to SymbolicPCC (ablation)SymbolicPCC · Mininet lossy networkLossy mean throughput: 28.40 -> 28.55Improved
Add context-specific branches and a branch decider to SymbolicPCC (ablation)SymbolicPCC · Mininet lossy networkLossy total throughput: 738.46 -> 742.46Improved
Add context-specific branches and a branch decider to SymbolicPCC (ablation)SymbolicPCC · Mininet lossy networkLossy mean squared error to optimal: 7.29 -> 4.14Improved
Add context-specific branches and a branch decider to SymbolicPCC (ablation)SymbolicPCC · Mininet oscillating networkOscillating mean squared error to optimal: 85.03 -> 43.83Improved
Add context-specific branches and a branch decider to SymbolicPCC (ablation)SymbolicPCC · CC agent inferenceRuntime (μs): 23 -> 37Hurt
Distill Aurora into a symbolic policyAurora · Mininet lossy networkLossy mean squared error to optimal: 26.29 -> 7.29Improved
Distill Aurora into a symbolic policyAurora · CC agent inferenceRuntime (μs): 864 -> 23Improved
Prune Aurora by 50%Aurora · Mininet lossy networkLossy mean throughput: 27.55 -> 27.03Hurt
Prune Aurora by 80%Aurora · Mininet lossy networkLossy mean throughput: 27.55 -> 26.42Hurt
Prune Aurora by 95%Aurora · Mininet lossy networkLossy mean throughput: 27.55 -> 25.97Hurt
Quantize AuroraAurora · Mininet lossy networkLossy mean throughput: 27.55 -> 22.54Hurt
Distill Aurora into a 50%-size black-box model, then distill that model symbolicallyAurora · PCC-RLAverage return: 832 -> 641 -> 687Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy