Research map / Multi-agent systems and games / Cooperative multi-agent RL
MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning
Tianmeng Hu, Biao Luo, Chunhua Yang, Tingwen Huang
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 MO-MIX instead of outer-loop QMIX trained per preference | multi-objective multi-agent RL · MPE | hypervolume: 9448.3380 -> 11080.9224 | Improved |
| use MO-MIX instead of outer-loop QMIX | multi-objective multi-agent RL · MPE | training episodes: 1,025,000 -> 75,000 | Improved |
| use MO-MIX instead of outer-loop QMIX | multi-objective multi-agent RL · SMAC 2s3z | hypervolume: 6226.9744 -> 7371.7852 | Improved |
| use MO-MIX instead of outer-loop QMIX | multi-objective multi-agent RL · SMAC 2s3z | training steps: 41 million -> 5 million | Improved |
| increase preference sampling density of outer-loop QMIX (interval 0.025 to 0.01, 101 rounds) | Outer-loop QMIX · MPE | hypervolume: 9448.3380 -> 9791.7632 | No clear effect |
| reduce MO-MIX preference sampling interval from 0.0125 to 0.01 (ablation) | MO-MIX · MPE | hypervolume, diversity, spacing, sparsity | No clear effect |
| use coarser preference sampling interval (0.05 or 0.025 instead of 0.0125) (ablation) | MO-MIX · MPE | hypervolume, diversity, spacing, sparsity | Hurt |
| add the exploration guide (ablation) | MO-MIX · MPE | hypervolume, diversity, spacing, sparsity | Improved |
Later papers that compared with this method
1 later accepted paper reports MOMIX as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning (AAAI 2026 · better on 3 of 3 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
- Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks (NeurIPS 2021 · similarity 0.89)
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.88)
- MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees (TPAMI 2025 · similarity 0.88)
- A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning (NeurIPS 2023 · similarity 0.88)
- Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach (NeurIPS 2025 · similarity 0.87)
- Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning (ICML 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.
