Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game
Zhiyuan YAO, Zihan Ding
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 |
|---|---|---|---|
| add log term to VBF reward (ablation) | Distr-LB · Real-world moderate, Period III Wiki | average QoS (s): 0.159 -> 0.108 | Improved |
| add log term to VBF reward (ablation) | Distr-LB · Real-world moderate, Period IV Static | average QoS (s): 0.032 -> 0.006 | Improved |
| add log term to VBF reward (ablation) | Distr-LB · Simulator 50%-CPU+50%-IO | average QoS (s): 10.335 -> 8.797 | Improved |
| add log term to VBF reward (ablation) | Distr-LB · Simulator 100%-CPU | average QoS (s): 1.643 -> 2.004 | Hurt |
| add log term to VBF reward (ablation) | Distr-LB · Simulator 75%-CPU+25%-IO | average QoS (s): 1.695 -> 1.873 | Hurt |
| add log term to VBF reward (ablation) | Distr-LB · Real-world large, Period I Wiki | average QoS (s): 0.228 -> 0.161 | Improved |
| use distributed Distr-LB instead of centralised Centr-LB | Distr-LB · Real-world moderate, Period III Wiki | average QoS (s): 0.759 -> 0.108 | Improved |
| use Distr-LB instead of SED | Distr-LB · Real-world moderate, Period III Static | average QoS (s): 0.051 -> 0.004 | Improved |
| use Distr-LB instead of RLB-SAC (G) | Distr-LB · Real-world moderate, Period IV Wiki | average QoS (s): 0.155 -> 0.104 | Improved |
| use Distr-LB (VBF) instead of QMix-LB (PBF) | Distr-LB · Simulator 100%-CPU | average QoS (s): 2.200 -> 1.643 | Improved |
| use Distr-LB (VBF+logVBF) instead of QMix-LB (VBF) | Distr-LB · Real-world moderate, Period IV Wiki | average QoS (s): 0.286 -> 0.104 | Improved |
| use Distr-LB instead of QMix-LB (VBF) | Distr-LB · Real-world moderate, Period III Wiki | average QoS (s): 0.141 -> 0.159 | No clear effect |
Closest papers by meaning
- Secure Multi-agent Reinforcement Learning for Service Systems with Affinity and Byzantine Nodes: Stability Analysis and Protection Design (ICML 2026 · similarity 0.87)
- Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games (ICML 2021 · similarity 0.87)
- Learning to Share in Networked Multi-Agent Reinforcement Learning (NeurIPS 2022 · similarity 0.86)
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.86)
- SustainDC: Benchmarking for Sustainable Data Center Control (NeurIPS 2024 · similarity 0.85)
- Decomposing Temporal Equilibrium Strategy for Coordinated Distributed Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.85)
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.
