LBF
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-agent Coordination | LBF 3p-1f | Average Win Rate77 | 16 | |
| LBF task stream | LBF (Medium) | Backward Transfer3.12 | 8 | |
| LBF task stream | LBF (Expert) | Backward Transfer0.46 | 8 | |
| Offline Multi-Agent Sequential Decision Making | LBF 11×11-6p-4f | Win Rate96 | 8 | |
| Multi-agent Continual Cooperation | LBF Medium | Forward Transfer-0.36 | 7 | |
| Multi-agent Continual Cooperation | LBF (Expert) | Forward Transfer-0.42 | 7 | |
| Multi-Agent Reinforcement Learning | LBF 8x8-3p-2f | Success Rate (SR)95.9 | 4 | |
| Level Based Foraging (LBF) | LBF roster (test) | Returns (x1e2)8.98 | 4 | |
| Level Based Foraging (LBF) | LBF (val) | Returns0.0447 | 4 | |
| Level Based Foraging (LBF) | LBF (train) | Returns791 | 4 | |
| Multi-Agent Reinforcement Learning | LBF | Success Rate95.9 | 2 |
Showing 11 of 11 rows