List your company

Offline Reinforcement Learning on D4RL halfcheetah v2 (medium-replay)

76.9Normalized ScoreCQL
13.14829.69946.2562.801Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026

Evaluation results

MethodLinks
CQL2022.1076.9
PhyBModel category=Model-based2026.0574.7
PMDB2022.1071.7
PMDBN=10, k=22022.1071.7
PMDBModel category=Model-based2026.0571.7
MOPO2026.0269.2
RAMBO2022.1068.7
RAMBOModel category=Model-based2026.0568.7
ADMModel category=Model-based2026.0567.6
EPQModel category=Model-free2026.0562
EDAC2022.1061.3
EDAC2022.1061.3
EDAC-102026.0260.1
Uncertainty-Aware Rank-One MIMO Q Network2026.0259.9
CPED2023.0155.8
COMBOCategory=Model-based RL2024.0555.1
MOPO2023.1153.1
MOPOCategory=Model-based RL2024.0553.1
SPOT2023.0152.2
FQLModel category=Model-free2026.0552.2
DMGModel category=Model-free2026.0551.4
BEAR2022.1048.6
BRAC2022.1048.6
BRAC-v2026.0147.7
CQL2026.0146.2
CQL2023.0145.5
CQL2026.0245.5
BRAC2022.1045.3
CQL2022.1045.3
CQLModel category=Model-free2026.0545.3
PBRL2026.0245.1
TD3+BC2023.0144.6
TD3+BC2026.0144.6
TD3-BC2026.0244.6
MOREL2022.1044.5
MOReL2022.1044.5
MOReLModel category=Model-based2026.0544.5
IQL2023.0144.2
IQL2026.0144.2
TD3+BCModel category=Model-free2026.0543.3
LSDT2026.0142.9
TAILO2023.1142.8
IQL2026.0242.5
AWAC2023.0140.5
MOReL2023.1140.2
MORELCategory=Model-based RL2024.0540.2
BEAR2022.1039.4
VDT2026.0139.4
DDCategory=Diffusion Planner2024.0539.3
BCQ2026.0239
AdaptDiffuserCategory=Diffusion Planner2024.0538.3
Onestep RL2023.0138.1
DDT2026.0137.8
DiffuserCategory=Diffusion Planner2024.0537.7
BC2022.1037.6
BC2022.1037.6
BC2023.0136.6
DT2023.0136.6
BEAR2026.0236.3
DT2026.0136.2
UWAV2026.0235.9
DROCOShift Type=Kinematic2025.1226.9
BOSAShift Type=Kinematic2025.1226.3
CQLShift Type=Kinematic2025.1223.6
IGDFShift Type=Kinematic2025.1222.9
IQLShift Type=Kinematic2025.1222.1
DARAShift Type=Kinematic2025.1221.6
OTDFShift Type=Kinematic2025.1215.6