Multi-Agent Reinforcement Learning on Gaussian Squeeze N=10,000 (Mixed)
80.2Normalized ReturnMF-Diffuser
Evaluation results
| Method | Links | |
|---|---|---|
| MF-Diffuser2026.05 | 80.2 | |
| MF-CDMs-RL2026.05 | 71.2 | |
| Oryx2026.05 | 70 | |
| MFQ-Offline2026.05 | 62.7 | |
| DoF2026.05 | 29.4 | |
| Indep. Diffuser2026.05 | 25.8 | |
| MA-TD3+BC2026.05 | 7.6 | |
| MADiffattention=chunked-attention (max 12-agent windows)2026.05 | 4.5 | |
| OMAR2026.05 | 4.1 | |
| Joint Diffuserattention=chunked-attention (block size 32)2026.05 | 2.7 |