Research map / Multi-agent systems and games / Cooperative multi-agent RL
Autonomous Partner Selection for Cooperative Multi-Agent Reinforcement Learning
Rui Tang, Biao Luo, Yongzheng Cui
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 |
|---|---|---|---|
| remove information distillation (intention encoder trained against attention output) (ablation) | APS · SMAC 3s5z_vs_3s6z, 6h_vs_8z and GRF academy_counterattack_hard | test win rate | Improved |
| add contrastive tendency differentiation to agents' intention embeddings (ablation) | APS · SMAC and GRF maps | test win rate | Improved |
| add information distillation so agents extract cooperation cues from local observations (ablation) | APS · SMAC and GRF maps | test win rate | Improved |
| increase information distillation weight λi from 0.1 to 0.9 (ablation) | APS · SMAC 6h_vs_8z | test win rate | Hurt |
| increase contrastive weight λc from 0.01 to 0.09 (ablation) | APS · SMAC 6h_vs_8z | test win rate | Hurt |
| use APS instead of QMIX, QPLEX, MAPPO, RIIT, Gomarl, ACORM, GACG | QMIX backbone · 6 SMAC maps | test win rate | Improved |
| use APS instead of baselines on sparse-reward GRF | QMIX backbone · GRF academy_counterattack_hard and two other academy maps | test win rate | Improved |
Closest papers by meaning
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.88)
- N-agent Ad Hoc Teamwork (NeurIPS 2024 · similarity 0.88)
- Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Learning Joint Behaviors with Large Variations (AAAI 2025 · similarity 0.87)
- Adaptively Coordinating with Novel Partners via Learned Latent Strategies (NeurIPS 2025 · similarity 0.87)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.87)
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.
