List your company

Offline Reinforcement Learning on D4RL hopper-full-replay v2

111Normalized ScorePhyB
16.25640.85365.4590.047Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.05111
PMDB2022.10109.1
PMDBN=10, k=22022.10109.1
PMDBNumber of random seeds=42026.03109.1
PMDBModel category=Model-based2026.05109.1
RRPINumber of random seeds=42026.03108.6
EPQNumber of random seeds=42026.03108.5
AMGNumber of random seeds=42026.03108.5
EPQModel category=Model-free2026.05108.5
ADMModel category=Model-based2026.05108.5
BRAC2022.10107.4
DMGNumber of random seeds=42026.03106.4
DMGModel category=Model-free2026.05106.4
EDAC2022.10105.4
EDAC2022.10105.4
RAMBO2022.10105.2
RAMBONumber of random seeds=42026.03105.2
RAMBOModel category=Model-based2026.05105.2
BRAC2022.10101.9
CQL2022.10101.9
CQLNumber of random seeds=42026.03101.9
CQLModel category=Model-free2026.05101.9
CQL2022.10101
MOREL2022.1094.4
MOReL2022.1094.4
MOReLNumber of random seeds=42026.0394.4
MOReLModel category=Model-based2026.0594.4
FQLModel category=Model-free2026.0589.6
TD3+BCModel category=Model-free2026.0585.9
BEAR2022.1054
BEAR2022.1054
BC2022.1019.9
BC2022.1019.9