Leopard: a Pragmatic Learning-Based Multipath Congestion Control for Rapid Adaptation to New Network Conditions

Multipath TCP is a multipath transport protocol deployed on end devices, and many learning-based multipath congestion control schemes have been proposed and verified. However, these schemes cannot adapt rapidly to new network conditions because of their convergence problems and generalization issues. To rapidly adapt to new network conditions, we propose Leopard, a learning-based multi-path congestion control framework that uses reinforcement learning to combine offline learning with online fine-tuning. The extensive experiments in emulated network conditions and the real world demonstrate that Leopard converges quickly and maintains consistent high performance in new network conditions, which avoids long retraining when the network environment changes. Leopard improves throughput by 13% compared with DRL-CC and reduces the convergence time by 20% compared with MPCC in new network conditions.