Research map / Multi-agent systems and games / Cooperative multi-agent RL
Reinforcement Learning with Fuzzy Human Attention-Guided Graph for Heterogeneous Multiagent Systems
Dingbang Liu, Fenghui Ren, Jun Yan, Guoxin Su, Shohei Kato, Wen Gu
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 fuzzy human attention-guided graph (HAGG) | Qatten · SMAC hard/super hard heterogeneous maps | test win rate | Improved |
| add HAGG | QPLEX · SMACv2 5 vs 5 | test win rate | Improved |
| add HAGG to various value and policy based algorithms (ablation) | MARL baselines · 5m vs 6m, MMM2 | test win rate | Improved |
| use higher-quality human attention knowledge (ablation) | HAGG with Qatten · 5m vs 6m, MMM2 | test win rate | Improved |
| add noisy inappropriate guidance (ablation) | HAGG with Qatten · 5m vs 6m, MMM2 | test win rate | No clear effect |
| replace hyper-network with MLP fine-tuning (ablation) | HAGG with Qatten · 5m vs 6m, MMM2 | test win rate | Hurt |
| replace human attention guidance with graph learned from scratch (attention encoder) (ablation) | HAGG with Qatten · 5m vs 6m, MMM2 | test win rate | Hurt |
| increase number of agents (8m vs 9m, 18m vs 20m) | HAGG with Qatten · scalability | test win rate | Improved |
Closest papers by meaning
- Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems (NeurIPS 2024 · similarity 0.92)
- HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network (ICML 2024 · similarity 0.88)
- HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.87)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.87)
- Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning (NeurIPS 2025 · 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.
