Multi-agent Reinforcement Learning on SMAC 6h_vs_8z
Metric: Median Win Rate (higher is better)
Metric: Median Win Rate (higher is better)
| # | Model↕ | Median Win Rate▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ACE | 93.75 | No | ACE: Cooperative Multi-agent Q-learning with Bid... | 2022-11-29 | Code |
| 2 | DDN | 83.92 | No | DFAC Framework: Factorizing the Value Function v... | 2021-02-16 | Code |
| 3 | DMIX | 49.43 | No | DFAC Framework: Factorizing the Value Function v... | 2021-02-16 | Code |
| 4 | DPLEX | 43.75 | No | A Unified Framework for Factorizing Distribution... | 2023-06-04 | Code |
| 5 | QMIX | 12.78 | No | DFAC Framework: Factorizing the Value Function v... | 2021-02-16 | Code |
| 6 | QMIX | 3 | No | Monotonic Value Function Factorisation for Deep ... | 2020-03-19 | Code |
| 7 | QMIX | 3 | No | Monotonic Value Function Factorisation for Deep ... | 2020-03-19 | Code |
| 8 | VDN | 0 | No | - | - | Code |
| 9 | DIQL | 0 | No | - | - | Code |
| 10 | IQL | 0 | No | - | - | Code |
| 11 | IQL | 0 | No | - | - | Code |
| 12 | VDN | 0 | No | - | - | Code |
| 13 | Heuristic | 0 | No | - | - | Code |