List your company

Offline Reinforcement Learning on D4RL Hopper-medium-replay v2

110.7Normalized ReturnPhyB
3.5831.3959.287.01Feb 13, 2022Nov 1, 2022Jul 20, 2023Apr 6, 2024Dec 23, 2024Sep 10, 2025May 30, 2026

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.05110.7
EDAC2022.10107.4
PMDB2022.10106.2
PMDBModel category=Model-based2026.05106.2
ADMModel category=Model-based2026.05104.4
Uncertainty-Aware Rank-One MIMO Q Network2026.02102.9
EDAC-102026.02102.8
DMGModel category=Model-free2026.05101.9
PBRL2026.02100.6
SPOT2022.02100.2
SPOT2023.01100.2
RAMBO2022.1099.5
RAMBOModel category=Model-based2026.0599.5
CPED2023.0198.1
EPQModel category=Model-free2026.0597.8
Onestep2022.0297.5
Onestep RL2023.0197.5
CQL2022.0295
CQL2023.0195
IQL2022.0294.7
IQL2023.0194.7
MOReL2023.1193.6
CQL2026.0288.7
CQL2022.1086.3
CQLModel category=Model-free2026.0586.3
TAILO2023.1183.4
DT2022.0282.7
DT2023.0182.7
IQL2026.0281.9
MOREL2022.1081.8
MOReLModel category=Model-based2026.0581.8
GACStrategy=Exploitation query (GAC-E[y])2025.1280.1
LPT2025.1271.2
MOPO2023.1167.5
GACStrategy=Exploration query (GAC-p(y+))2025.1267.5
BRAC2022.1062.7
GACStrategy=Fixed target steering (GAC-y*)2025.1261.3
TD3+BC2022.0260.9
TD3+BC2023.0160.9
TD3-BC2026.0260.9
BEAR2022.1057.7
BEAR2026.0252.2
DT2025.1250.8
DROCOShift Type=Kinematic2025.1247.3
CQLShift Type=Kinematic2025.1243.2
DARAShift Type=Kinematic2025.1241.6
FQLModel category=Model-free2026.0540.6
IQLShift Type=Kinematic2025.1240.2
QDT2025.1238.7
AWAC2022.0237.2
AWAC2023.0137.2
GACStrategy=Sampling from prior (p(y|z)p(z))2025.1234.3
MOPO2026.0232.7
TD3+BCModel category=Model-free2026.0531.4
IGDFShift Type=Kinematic2025.1230
BOSAShift Type=Kinematic2025.1229.5
OTDFShift Type=Kinematic2025.1226.2
UWAV2026.0225.3
BC2022.0218.1
BC2023.0118.1
BC2022.1016.6
IQL2025.1213.9
BCQ2026.0211.1
CQL2025.127.7