Research map / Multi-agent systems and games / Cooperative multi-agent RL
MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control
Xuehai Pan, Mickel Liu, fangwei zhong, Yaodong Yang, Song-Chun Zhu, Yizhou Wang
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 |
|---|---|---|---|
| switch from full to partial observability (ablation) | IPPO · 2C vs. 4T (0O) | normalized episode reward: approximately 0.35 decrease | Hurt |
| switch from full to partial observability (ablation) | MAPPO · 2C vs. 4T (0O) | normalized episode reward | No clear effect |
| switch from full to partial observability (ablation) | MAPPO · 4C vs. 8T (0O) | normalized episode reward: approximately 0.1 decrease | Hurt |
| switch from full to partial observability (ablation) | IPPO · 4C vs. 8T (0O) | normalized episode reward | Hurt |
| add multi-agent communication (TarMAC/I2C) to MAPPO camera agents (ablation) | MAPPO with HRL · 4C vs. 8T (9O) camera training | Mean Coverage Rate | No clear effect |
| add communication module to target agents (ablation) | MARL target agents · target training vs greedy cameras | normalized episode reward | Improved |
| train against evolving opponents (PSRO-Nash, self-play) instead of fixed-policy opponents (ablation) | camera and target populations · MATE competitive game | exploitability | Improved |
| use Fictitious Self-Play uniform sampling instead of PSRO-Nash (ablation) | camera and target populations · MATE competitive game | exploitability | Hurt |
Closest papers by meaning
- FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.87)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.87)
- POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding (ICLR 2025 · similarity 0.86)
- ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination (NeurIPS 2024 · similarity 0.86)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.86)
- A Generalist Hanabi Agent (ICLR 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.
