Multi-agent Reinforcement Learning on SMAC 2s_vs_1sc
78Win RateSeqComm-DFL
Evaluation Results
| Method | Links | |
|---|---|---|
| SeqComm-DFLTraining Iterations=10M2026.04 | 78 | |
| SeqCommTraining Iterations=10M2026.04 | 65 | |
| OMDTraining Iterations=10M2026.04 | 52 |
Loading the SOTA2 catalog…