Multi-Agent Reinforcement Learning on SMAC complete benchmark 10 seeds
78Win Rate (2s_vs_1sc)SeqComm-DFL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SeqComm-DFL2026.04 | 78 | 71 | 64 | 59 | |
| Orig. SeqComm2026.04 | 65 | 58 | 49 | 45 | |
| OMD2026.04 | 52 | 41 | 35 | 31 |
Loading the SOTA2 catalog…