List your company
ResearchFormerly WizWand

Multi-agent Reinforcement Learning on MPE Cooperative Navigation (CN) v1 (Expert)

126.3Normalized ScoreDoF-P
7.63638.44369.25100.057Sep 22, 2023Dec 30, 2023Apr 7, 2024Jul 15, 2024Oct 22, 2024Jan 29, 2025May 9, 2025
Updated 5mo ago

Evaluation results

MethodLinks
DoF-P2025.05126.3
OMAR2023.09114.9
OMAR2025.05114.9
CFCQL2023.09112
CFCQL2025.05112
MACCA-OMARBackbone=OMAR2023.12111.7
MA-TD3+BC2025.05108.3
MA-ICQ2025.05104
IQL2023.09103.7
OMSD2025.05102.3
MA-CQL2025.0598.2
MADiff-D2025.0595
MACCA-ICQBackbone=ICQ2023.1290.4
MACCA-CQLBackbone=CQL2023.1285.4
MA-ICQFramework=CTDE2023.1245
OMAROptimization=zeroth-order optimization2023.1244.7
BC2025.0535
I-CQLFramework=Independent Learning2023.1233.6
MACQL2023.0912.2