Research map / Multi-agent systems and games / Cooperative multi-agent RL
Multi-Agent Determinantal Q-Learning
Yaodong Yang, Ying Wen, Jun Wang, Liheng Chen, Kun Shao, David Mguni, Weinan Zhang
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 Q-DPP instead of existing CTDE baselines | Cooperative multi-agent tasks · Pathological Stochastic Game | reward | Improved |
| Use Q-DPP instead of existing CTDE baselines | Cooperative multi-agent tasks · Blocker Game | reward | Improved |
| Use Q-DPP instead of existing CTDE baselines | Cooperative multi-agent tasks · Coordinated Navigation | reward | Improved |
| Use Q-DPP instead of existing CTDE baselines | Cooperative multi-agent tasks · Predator-Prey World | reward | Improved |
| Add the singular-value constraint auxiliary loss (ablation) | Q-DPP · Blocker Game and Coordinated Navigation | reward | No clear effect |
| Add the singular-value constraint auxiliary loss (ablation) | Q-DPP · Blocker Game and Coordinated Navigation | reward variance | Improved |
| Increase the diversity term's relative contribution during training | Q-DPP · Blocker Game | quality-diversity ratio | Mixed |
Closest papers by meaning
- Q-value Path Decomposition for Deep Multiagent Reinforcement Learning (ICML 2020 · similarity 0.89)
- QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning (ICML 2019 · similarity 0.89)
- Determinantal Reinforcement Learning (AAAI 2019 · similarity 0.89)
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · similarity 0.89)
- MADiff: Offline Multi-agent Learning with Diffusion Models (NeurIPS 2024 · similarity 0.87)
- High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning (NeurIPS 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.
