List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL halfcheetah-expert v2

113.7Normalized ScorePhyB
-1.53228.38458.388.216Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026
Updated 5mo ago

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.05113.7
EPQModel category=Model-free2026.05107.2
EDAC2022.10106.8
EDAC2022.10106.8
PMDB2022.10105.7
PMDBN=10, k=22022.10105.7
TD3+BCModel category=Model-free2026.05105.7
PMDBModel category=Model-based2026.05105.7
Uncertainty-Aware Rank-One MIMO Q Network2026.02105.4
EDAC-102026.02104
CQL2022.1097.3
CQL2022.1097.3
CQLModel category=Model-free2026.0597.3
CEILProtocol=C-off-LfD, Trials=302023.0697.1
CEILProtocol=S-off-LfO, Trials=302023.0696.8
TD3-BC2026.0296.7
CQL2026.0296.3
CEILProtocol=S-off-LfD, Trials=302023.0696
DMGModel category=Model-free2026.0595.9
IQL2026.0294.8
SMODICEProtocol=C-off-LfD, Trials=302023.0693.8
SMODICEProtocol=S-off-LfO, Trials=302023.0693.7
SMODICEProtocol=C-off-LfO, Trials=302023.0693.7
SMODICEProtocol=S-off-LfD, Trials=302023.0693.5
Decision Mamba2024.0693.5
UWAV2026.0292.9
BEAR2026.0292.7
BEAR2022.1092.6
BEAR2022.1092.6
PBRL2026.0292.4
ORIL (TD3+BC)Protocol=S-off-LfO, Trials=302023.0692.1
LaMo2024.0692
BC2022.1091.8
BC2022.1091.8
ORIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.0691.8
DT2024.0690.5
BCQ2026.0290.4
CEILProtocol=C-off-LfO, Trials=302023.0690.1
ADMModel category=Model-based2026.0589.4
DemoDICEProtocol=C-off-LfD, Trials=302023.0688.7
DemoDICEProtocol=S-off-LfD, Trials=302023.0687.1
BOSAShift Type=Kinematic2025.1284.3
BC2024.0683.3
MOPO2026.0281.3
OTDFShift Type=Kinematic2025.1279.6
RAMBO2022.1079.3
RAMBOModel category=Model-based2026.0579.3
ORIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.0678.3
ORIL (TD3+BC)Protocol=C-off-LfO, Trials=302023.0676.6
DROCOShift Type=Kinematic2025.1267.4
IQLShift Type=Kinematic2025.1249.7
IGDFShift Type=Kinematic2025.1247.6
DARAShift Type=Kinematic2025.1247.4
BRAC2022.1039
BRAC2022.1039
CQLShift Type=Kinematic2025.1236
IQ-LearnProtocol=C-off-LfD, Trials=302023.0631.2
SQIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.0619.9
SQIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.0614.4
IQ-LearnProtocol=S-off-LfD, Trials=302023.069.9
ValueDICEProtocol=C-off-LfD, Trials=302023.069.8
MOREL2022.108.4
MOReL2022.108.4
MOReLModel category=Model-based2026.058.4
FQLModel category=Model-free2026.054.4
ValueDICEProtocol=S-off-LfD, Trials=302023.062.9