Multi-agent Reinforcement Learning on SMAC (various scenarios)
6Best OutcomeMRVF
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MRVFEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 6 | 0 | |
| NA^2QEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 4 | 0 | |
| QMIXEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 3 | 1 | |
| RESQEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 3 | 1 | |
| QPLEXEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 1 | 3 | |
| QTRANEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 1 | 5 | |
| WQMIXEvaluation period=averaged over steps after 1.5M, Tolerance=±0.052026.04 | 1 | 2 |