Research map / Multi-agent systems and games / Cooperative multi-agent RL
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
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 |
|---|---|---|---|
| Add the shared Knowledge Source to the critic (ablation) | SAF · HECOGrid cooperative tasks | performance | Helped |
| Add the shared policy pool (ablation) | SAF · HECOGrid tasks with environmental heterogeneity | performance | Helped |
| Add the shared policy pool (ablation) | SAF · HECOGrid tasks requiring high coordination | performance | No clear effect |
| Add the shared policy pool (ablation) | QPLEX · HECOGrid environments with 5 agents and high coordination | learning efficiency | Helped |
| Train with a shared policy pool (ablation) | SAF · TeamTogether, unseen coordination levels | performance | Helped |
| Train with a shared policy pool (ablation) | SAF · HECOGrid, unseen heterogeneity levels | performance | Helped |
| Increase coordination level from 1 to 2 | IPPO, MAPPO, and SAF · HECOGrid: TeamTogether, TeamSupport, KeyForTreasure | performance: more than 50% decrease | Hurt |
| Increase coordination level to 3 | IPPO, MAPPO, and SAF · HECOGrid: TeamTogether, TeamSupport, KeyForTreasure | performance | Hurt |
| Increase environmental heterogeneity | IPPO, MAPPO, and SAF · HECOGrid: TeamTogether, TeamSupport, KeyForTreasure | performance | Hurt |
| Use SAF instead of IPPO or MAPPO | Cooperative MARL agents · HECOGrid tasks across coordination and heterogeneity levels | performance | Helped |
| Train at coordination level 2 and test at different coordination levels | SAF versus MAPPO · TeamSupport | performance | Mixed |
| Train at coordination level 2 and test at different coordination levels | SAF versus IPPO and MAPPO · TeamTogether | performance | Helped |
Closest papers by meaning
- ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (ICLR 2025 · similarity 0.89)
- Heterogeneous Agent Collaborative Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.88)
- Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Graph Diffusion for Robust Multi-Agent Coordination (ICML 2025 · similarity 0.88)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.88)
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.