Multi-agent Reinforcement Learning on SMAC 3s_vs_5z
71Win RateSeqComm-DFL
Evaluation Results
| Method | Links | |
|---|---|---|
| SeqComm-DFLTraining Iterations=10M2026.04 | 71 | |
| SeqCommTraining Iterations=10M2026.04 | 58 | |
| OMDTraining Iterations=10M2026.04 | 41 |
Loading the SOTA2 catalog…