Research map / Multi-agent systems and games / Cooperative multi-agent RL
VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning
Qian Zhang, Zhuo Sun, Yao Zhang, Zhiwen Yu, Bin Guo, Jun Zhang
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 ResoNet VoI-aware resource allocation (ablation) | VIL2C · SMACv2 10gen terran | win rate: 0.28 -> 0.55 | Improved |
| add ResoNet VoI-aware resource allocation (ablation) | VIL2C · SMACv2 10gen zerg | win rate: 0.41 -> 0.48 | Improved |
| add Progressive Reception (ablation) | VIL2C · SMACv2 10gen protoss | win rate: 0.32 -> 0.42 | Improved |
| add Progressive Reception (ablation) | VIL2C · SMACv2 10gen zerg | win rate: 0.28 -> 0.48 | Improved |
| add naive communication (I2C, equal allocation) to MAPPO under latency | MAPPO · Predator-Prey | reward | Hurt |
| VIL2C instead of baselines under latency | MAPPO with communication · Predator-Prey, Cooperative Navigation | reward | Improved |
| increase maximum waiting time (ablation) | VIL2C · Predator-Prey | reward | Mixed |
| reduce bandwidth/power budget (ablation) | VIL2C · Predator-Prey | reward | Hurt |
Closest papers by meaning
- DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning (AAAI 2023 · similarity 0.91)
- Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control (NeurIPS 2019 · similarity 0.89)
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors (NeurIPS 2025 · similarity 0.89)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · similarity 0.86)
- Robust Communicative Multi-Agent Reinforcement Learning with Active Defense (AAAI 2024 · similarity 0.86)
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.
