Research map / Multi-agent systems and games / Cooperative multi-agent RL
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning
Hangyu Mao, Wulong Liu, Jianye Hao, Jun Luo, Dong Li, Zhengchao Zhang, Jun Wang, Zhen Xiao
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 |
|---|---|---|---|
| Use neighborhood cognitive consistency instead of a critic without cognitive-consistency loss (ablation) | NCC-AC · Packet routing | reward | Improved |
| Enforce global cognitive consistency instead of neighborhood cognitive consistency (ablation) | NCC-AC · Packet routing | reward | Hurt |
| Use neighborhood cognitive consistency instead of a critic without cognitive-consistency loss (ablation) | NCC-Q · WiFi configuration | reward | Improved |
| Use neighborhood cognitive consistency instead of global cognitive consistency (ablation) | NCC-Q · WiFi configuration | reward | Improved |
| Use neighborhood cognitive consistency instead of a critic without cognitive-consistency loss (ablation) | NCC-Q · Google football | reward | Improved |
| Add CD-loss to TD-loss training (ablation) | NCC-Q · Google football 2-vs-2, game difficulty 0.6 | reward | Improved |
| Add CD-loss to TD-loss training (ablation) | NCC-Q · Google football 2-vs-2, game difficulty 0.9 | reward | Improved |
| Use NCC-AC rather than ATT-MADDPG or MADDPG | Packet routing · Middle topology | reward | Improved |
| Use NCC-AC rather than ATT-MADDPG or MADDPG | Packet routing · Large topology | reward | Improved |
| Use NCC-Q rather than the other evaluated methods | NCC-Q · WiFi configuration | reward | Improved |
| Use NCC-Q rather than the other evaluated methods | NCC-Q · Google football | reward | Improved |
Closest papers by meaning
- A Generalist Hanabi Agent (ICLR 2025 · similarity 0.86)
- Investigating Relational State Abstraction in Collaborative MARL (AAAI 2025 · similarity 0.86)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.85)
- Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning (AAAI 2026 · similarity 0.85)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.85)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 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.
