List your company

Offline Reinforcement Learning on D4RL halfcheetah-full-replay v2

98.1Normalized ScorePhyB
37.05252.90168.7584.599Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.0598.1
PMDB2022.1090
PMDBN=10, k=22022.1090
PMDBModel category=Model-based2026.0590
RAMBO2022.1087
RAMBOModel category=Model-based2026.0587
ADMModel category=Model-based2026.0586.3
EPQModel category=Model-free2026.0585.3
EDAC2022.1084.6
EDAC2022.1084.6
FQLModel category=Model-free2026.0580.9
DMGModel category=Model-free2026.0579.9
BRAC2022.1078
CQL2022.1076.9
CQL2022.1076.9
CQLModel category=Model-free2026.0576.9
BRAC2022.1075.1
TD3+BCModel category=Model-free2026.0571.9
MOREL2022.1070.1
MOReL2022.1070.1
MOReLModel category=Model-based2026.0570.1
BC2022.1062.9
BEAR2022.1060.1
BEAR2022.1060.1
BC2022.1039.4