List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on SMAC 3s5z vs 3s6z v2

0.801Win RateACL-LFT
0.711560.734780.7580.78122Oct 30, 2025
Updated 8mo ago

Evaluation results

MethodLinks
ACL-LFTRL-Method=QPLEX2025.100.801
ACL-LFTRL-Method=QMIX2025.100.794
ACL-LFTRL-Method=MAPPO2025.100.789
AMAGORL-Method=QPLEX2025.100.775
AMAGORL-Method=QMIX2025.100.763
AMAGORL-Method=MAPPO2025.100.761
MambaRL-Method=QMIX2025.100.751
ToSTRL-Method=QPLEX2025.100.751
MambaRL-Method=QPLEX2025.100.75
ToSTRL-Method=QMIX2025.100.737
TransformerRL-Method=QPLEX2025.100.736
TransformerRL-Method=QMIX2025.100.728
MambaRL-Method=MAPPO2025.100.726
ToSTRL-Method=MAPPO2025.100.722
TransformerRL-Method=MAPPO2025.100.715