Research map / Reinforcement learning / Visual and representation RL
Hierarchical Reinforcement Learning with Topology-Aware Exploration Framework for Multi-path Commodity Flow Problem
Jingchen Jiang, Xuan Zhou, Jiayuan Li, Geng Han, Xiang Shi, Fang Deng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| build paths end-to-end with a hierarchical RL agent instead of pre-generated KSP paths (HRL-TAE vs TEAL) | multi-path commodity flow · Abilene, ATT, Geant, DFN simulations | MLU: average improvement 7.08% | Improved |
| HRL-TAE vs TEAL in real SDN testbed | multi-path commodity flow · H9N and H18N real-world | MLU: average improvement 6.90% | Improved |
| add Quadruple Collaboration Training instead of basic REINFORCE for both layers (ablation) | HRL-TAE · 20 simulation cases | MLU: average improvement 8.86% | Improved |
| joint QCT training instead of alternating layer training (ablation) | HRL-TAE · 20 simulation cases | MLU: average improvement 4.75% | Improved |
| use QCT (ablation) | HRL-TAE · Geant training curves | training stability and efficiency | Improved |
| learned HRL-TAE vs TEAL on large topology | DFN · DFN cases 16-20 | solve time (s): 1.13 -> 0.12 (case 16) | Improved |
| HRL-TAE vs ECMP on ATT case 8 | HRL-TAE · ATT case 8 | MLU: 0.355 vs 0.385 | Improved |
Closest papers by meaning
- H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem (AAAI 2023 · similarity 0.86)
- Dynamic Latent Routing (NeurIPS 2026 · similarity 0.84)
- Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning (NeurIPS 2025 · similarity 0.84)
- Divide, Harmonize, Then Conquer It: Shooting Multi-Commodity Flow Problems with Multimodal Language Models (ICLR 2026 · similarity 0.84)
- NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation (NeurIPS 2024 · similarity 0.83)
- Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning (AAAI 2024 · similarity 0.83)
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.
