Research map / Multi-agent systems and games / Cooperative multi-agent RL
Self-Organized Polynomial-Time Coordination Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 dynamically selected polynomial-time coordination graphs instead of the complete graph | SOP-CG · MACO | return | Helped |
| Use SOP-CG with tree organization rather than the baselines | SOP-CG (G_T) · Tag | return | Helped |
| Use SOP-CG with action representation learning rather than DCG or CASEC | SMAC 10m_vs_11m and 1c3s5z · SMAC | performance | Helped |
| Add dynamic graph selection instead of using a fixed Line topology (ablation) | DCG (Line) versus SOP-CG · MACO | return | Mixed |
| Add dynamic graph selection instead of using a fixed Star topology (ablation) | DCG (Star) versus SOP-CG · MACO | return | Mixed |
| Add graph relabeling to the TD learning procedure (ablation) | SOP-CG · Pursuit | return | Helped |
| Add graph relabeling to the TD learning procedure (ablation) | SOP-CG · Tag | return | Helped |
| Replace the greedy tree-graph selection heuristic with exhaustive search (ablation) | SOP-CG (G_T) · Aloha | peak performance | No clear effect |
| Use exhaustive search rather than max-sum for action selection on a fixed, task-structure graph (ablation) | DCG on Aloha · Aloha | peak performance | Helped |
| Use pairwise grouping rather than tree organization (ablation) | SOP-CG · Pursuit | return | Helped |
| Use tree organization rather than pairwise grouping (ablation) | SOP-CG · Tag | return | Helped |
Closest papers by meaning
- Non-Linear Coordination Graphs (NeurIPS 2022 · similarity 0.92)
- Graph Diffusion for Robust Multi-Agent Coordination (ICML 2025 · similarity 0.90)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.88)
- HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.87)
- TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient (AAAI 2024 · similarity 0.86)
- Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning (AAAI 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.