Multi-Agent Reinforcement Learning on Gaussian Squeeze Expert N=10,000
90.5Normalized ReturnMF-Diffuser
Evaluation Results
| Method | Links | |
|---|---|---|
| MF-Diffuser2026.05 | 90.5 | |
| MF-CDMs-RL2026.05 | 88.5 | |
| Oryx2026.05 | 87.2 | |
| MFQ-Offline2026.05 | 79.3 | |
| DoF2026.05 | 58.7 | |
| Indep. Diffuser2026.05 | 52.5 | |
| MA-TD3+BC2026.05 | 26.8 | |
| OMAR2026.05 | 18.9 | |
| MADiffattention=chunked-attention (max 12-agent windows)2026.05 | 13.1 | |
| Joint Diffuserattention=chunked-attention (block size 32)2026.05 | 8.2 |