Research map / Multi-agent systems and games / Cooperative multi-agent RL
MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library
Siyi Hu, Yifan Zhong, Minquan Gao, Weixun Wang, Hao Dong, Xiaodan Liang, Zhihui Li, Xiaojun Chang, Yaodong Yang
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 MARLlib (Ray/RLlib workers) instead of EPyMARL | MAPPO training · SMAC MMM2, 15 workers | clock time (min:sec): 2:24 -> 1:24 | Improved |
| use MARLlib instead of official MAPPO | MAPPO training · SMAC MMM2, 5 workers | clock time (min:sec): 5:12 -> 3:29 | Improved |
| use MARLlib instead of EPyMARL | MAPPO training · SMAC MMM2, 10 workers | clock time (min:sec): 3:14 -> 2:16 | Improved |
| use MARLlib instead of EPyMARL | MAPPO training · SMAC MMM2, 15 workers | memory (GB): 15.8 -> 20.4 | Hurt |
| use MARLlib instead of EPyMARL | MAPPO training · SMAC MMM2, 5 workers | GPU memory (MB): 2245 -> 5025 | Hurt |
Closest papers by meaning
- Efficient Multi-agent Reinforcement Learning by Planning (ICLR 2024 · similarity 0.89)
- Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation (NeurIPS 2024 · similarity 0.88)
- FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.88)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 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.
