Research map / Multi-agent systems and games / Cooperative multi-agent RL
Correlated Policy Optimization in Multi-Agent Subteams
Dingyang Chen, Jianing Ye, Zhenyu Zhang, Xiaolong Kuang, Xinyang Shen, Ozalp Ozer, Chongjie Zhang, Qi 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 |
|---|---|---|---|
| use fewer, larger subteams (full DAG instead of product DAG) (ablation) | tabular softmax BN policy gradient · Coordination Game N=5 | normalized suboptimality | Improved |
| use full DAG instead of product DAG (ablation) | tabular softmax BN policy gradient · Coordination Game N=3 | normalized suboptimality | Improved |
| use 1+2 subteams instead of product (ablation) | tabular softmax BN policy gradient · Coordination Game N=3 | final performance: 2.94e-01 -> 3.96e-01 | No clear effect |
| use full DAG instead of product DAG (fitted transition error) (ablation) | BN policy · Coordination Game N=5 | decomposition error |eP|: 6.03e-01 -> 7.13e-08 | Improved |
| use dynamic heuristic DAG instead of random DAG under same edge budget (ablation) | MAPPO/MADDPG · Coordination Game, Aloha, Predator-Prey | reward | Improved |
| use heuristic DAG instead of full DAG (ablation) | MADDPG · Predator-Prey N=15 | reward | Improved |
| use heuristic subgroups instead of meta-learned subgroups | VAST · Warehouse N=16, Battle N=40 | reward | Improved |
| use full correlated DAG instead of product DAG (ablation) | MAPPO · SMAC bane vs. bane | win rate | No clear effect |
Closest papers by meaning
- Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning (ICML 2023 · similarity 0.91)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.89)
- AgentMixer: Multi-Agent Correlated Policy Factorization (AAAI 2025 · similarity 0.87)
- Graph Diffusion for Robust Multi-Agent Coordination (ICML 2025 · similarity 0.87)
- LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination (ICML 2025 · similarity 0.87)
- N-agent Ad Hoc Teamwork (NeurIPS 2024 · 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.
