Multi-Agent Reinforcement Learning on SMAC v2 (test)
84Win Rate (Protoss 5 Units)HPN-QMIX
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| HPN-QMIX2026.02 | 84 | 82 | 78 | — | |
| HPN-VDN2026.02 | 84 | 70 | 79 | — | |
| MMSA2026.02 | 81 | 83 | 81 | — | |
| QPLEX-ICES2025.09 | 74 | — | 48 | — | |
| QMIX-CERMIC2025.09 | 73 | — | 44 | — | |
| MAPPO-CERMIC2025.09 | 70 | — | 48 | — | |
| QMIX2026.02 | 69 | 75 | 73 | — | |
| MACE2025.09 | 67 | — | 44 | — | |
| QMIX-SPECTRA2025.09 | 65 | — | 45 | — | |
| CPM2025.09 | 64 | — | 44 | — | |
| SET-QMIX2026.02 | 63 | 64 | 64 | — | |
| MAPPO-DB2025.09 | 63 | — | 43 | — | |
| MAPPO2025.09 | 61 | — | 44 | — | |
| MAPPOexploration=epsilon greedy2025.09 | 61 | — | 43 | — | |
| QMIX2025.09 | 60 | — | 39 | — | |
| MAG2026.02 | 58 | 59 | 34 | — | |
| LMACEnvironment steps=3M2026.05 | 57.96 | 67.87 | 42.18 | — | |
| QMIX+STATEEnvironment steps=3M2026.05 | 56.4 | 64.77 | 40.06 | — | |
| MAMBA2026.02 | 54 | 54 | 32 | — | |
| MAICEnvironment steps=3M2026.05 | 51.93 | 63.8 | 38.59 | — | |
| QMIXEnvironment steps=3M2026.05 | 48.44 | 61.69 | 34.79 | — | |
| T2MACEnvironment steps=3M2026.05 | 48.16 | 61.67 | 35.09 | — | |
| NDQEnvironment steps=3M2026.05 | 48.03 | 59.2 | 38.75 | — | |
| VDN2026.02 | 46 | 67 | 62 | — | |
| MAPPO2026.02 | 38 | 45 | 29 | — | |
| STAIRS-Former2026.03 | 32.8 | 32.3 | 25 | 30 | |
| MASIAEnvironment steps=3M2026.05 | 32.43 | 54.72 | 34.22 | — | |
| HiSSD2026.03 | 28.5 | 25.1 | 18.8 | 24.1 | |
| SMSEnvironment steps=3M2026.05 | 27 | 34 | 13.53 | — | |
| TarMACEnvironment steps=3M2026.05 | 22.56 | 29.68 | 15.47 | — | |
| FullCommEnvironment steps=3M2026.05 | 16.93 | 18.44 | 6.83 | — | |
| ODIS2026.03 | 11.6 | 13.2 | 8 | 10.9 | |
| MADDPG2026.02 | 10 | 20 | 9 | — | |
| UPDeT-m2026.03 | 8.1 | 7 | 5 | 6.7 | |
| COLAEnvironment steps=3M2026.05 | 0.01 | 10.29 | 0.19 | — | |
| DGNBaseline Architecture=DGN2026.06 | — | — | — | 17.48 | |
| KNIFEBaseline Architecture=MAPPO2026.06 | — | — | — | 25.44 | |
| KNIFEBaseline Architecture=MADDPG2026.06 | — | — | — | 34.55 | |
| KNIFEBaseline Architecture=DGN2026.06 | — | — | — | 22.73 | |
| MADDPGBaseline Architecture=MADDPG2026.06 | — | — | — | 20.13 | |
| MAPPOBaseline Architecture=MAPPO2026.06 | — | — | — | 18.84 | |
| ReBornBaseline Architecture=MAPPO2026.06 | — | — | — | 17.61 | |
| ReBornBaseline Architecture=MADDPG2026.06 | — | — | — | 29.16 | |
| ReDoBaseline Architecture=MAPPO2026.06 | — | — | — | 20.26 | |
| ReDoBaseline Architecture=MADDPG2026.06 | — | — | — | 10.48 |