PolicyCache: Intra-flow Learning in Congestion Control

TCP congestion control (CC) schemes must balance fast responsiveness, adaptability to diverse network conditions, and low computational overhead. Existing approaches fall short: heuristic-based algorithms are lightweight but brittle, learningbased schemes provide high responsiveness yet struggle with generalization, and exploration-based methods adapt well but converge slowly. We present POLICYCACHE, the first CC algorithm based on intra-flow learning, where both training and execution of the policy are confined to a single flow. Unlike prior inter-flow learning, this paradigm avoids crossenvironment generalization pitfalls while maintaining high responsiveness. POLICYCACHE leverages a lightweight, nonparametric tree-based model coupled with online exploration and dynamic model switching to enable rapid and robust adaptation. We provide convergence analysis of POLICYCACHE and have built a fully functional Linux prototype. Extensive evaluations demonstrate that POLICYCACHE consistently achieves high throughput, low latency, and fairness across diverse emulated and real-world networks, while incurring minimal overhead. These results establish intra-flow learning as a practical and effective new direction for congestion control. Flows Trajectories Heuristicsbased CC Other flows Hand-craft ACK ACK Pkts Pkts (a) Heuristic-based CCA. Flows Training Data-1 Learned CC Policy Other flows Learning ACK ACK Pkts Pkts (b) Inter-flow Learning CCA.