Research map / Multi-agent systems and games / Cooperative multi-agent RL
Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning
Yitian Hong, Yaochu Jin, Yang Tang
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 |
|---|---|---|---|
| add IGM-DA (DAgger imitation) to QMIX | QMIX · SMAC sight view 0, average | win rate: 47.8 -> 68.9 | Improved |
| add IGM-DA to QPLEX | QPLEX · SMAC sight view 0, average | win rate: 41.0 -> 63.1 | Improved |
| add IGM-DA to DMIX | DMIX · SMAC sight view 0, average | win rate: 50.4 -> 67.0 | Improved |
| add IGM-DA to QMIX | QMIX · 3s_vs_5z | win rate: 1.9 -> 43.9 | Improved |
| add IGM-DA to QPLEX | QPLEX · MMM2 | win rate: 0.0 -> 55.4 | Improved |
| add IGM-DA to DMIX | DMIX · MMM2 | win rate: 0.0 -> 46.2 | Improved |
| add IGM-DA to QPLEX | QPLEX · 5m_vs_6m | win rate: 5.0 -> 38.9 | Improved |
| add IGM-DA to DMIX | DMIX · 8m_vs_9m | win rate: 64.7 -> 64.4 | No clear effect |
| add IGM-DA to DMIX | DMIX · 5m_vs_6m | win rate: 58.7 -> 59.0 | No clear effect |
| add IGM-DA to QMIX | QMIX · 8m | win rate: 98.3 -> 99.2 | No clear effect |
| add IGM-DA to DMIX | DMIX · 3s5z | win rate: 76.2 -> 91.7 | Improved |
| replace DAgger with Behavior Cloning (ablation) | IGM-DA · MMM2 | win rate | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- qmix — QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (ICML 2018) · better on 7 of 7 shared results
- qplex — QPLEX: Duplex Dueling Multi-Agent Q-Learning (ICLR 2021) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning (AAAI 2022 · similarity 0.88)
- Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning (AAAI 2026 · similarity 0.88)
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.87)
- Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · 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.
