List your company

Offline Reinforcement Learning on D4RL walker2d-expert v2

116.3Normalized ScorePhyB
-2.98827.98158.9589.919Oct 13, 2022May 21, 2023Dec 28, 2023Aug 5, 2024Mar 14, 2025Oct 21, 2025May 30, 2026

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.05116.3
PMDB2022.10115.9
PMDBN=10, k=22022.10115.9
PMDBModel category=Model-based2026.05115.9
CEILProtocol=S-off-LfD, Trials=302023.06115.6
EDAC2022.10115.1
EDAC2022.10115.1
DMGModel category=Model-free2026.05114.7
Uncertainty-Aware Rank-One MIMO Q Network2026.02112.7
BCQ2026.02110.4
TD3-BC2026.02110.2
BEAR2022.10110.1
BEAR2022.10110.1
CEILProtocol=S-off-LfO, Trials=302023.06110
EPQModel category=Model-free2026.05109.8
CQL2022.10109.3
CQL2022.10109.3
CQLModel category=Model-free2026.05109.3
IQL2026.02109
BC2022.10108.7
BC2022.10108.7
CEILProtocol=C-off-LfO, Trials=302023.06108.7
CEILProtocol=C-off-LfD, Trials=302023.06108.6
CQL2026.02108.5
UWAV2026.02108.4
Decision Mamba2024.06108.3
PBRL2026.02108.3
SMODICEProtocol=S-off-LfD, Trials=302023.06108.2
SMODICEProtocol=C-off-LfD, Trials=302023.06108.2
SMODICEProtocol=C-off-LfO, Trials=302023.06108.1
DT2024.06108.1
LaMo2024.06108.1
SMODICEProtocol=S-off-LfO, Trials=302023.06108
DemoDICEProtocol=C-off-LfD, Trials=302023.06107.9
BEAR2026.02106.6
DROCOShift Type=Kinematic2025.12106
TD3+BCModel category=Model-free2026.05105.7
DemoDICEProtocol=S-off-LfD, Trials=302023.06104.8
BC2024.06103.2
OTDFShift Type=Kinematic2025.1298.9
IGDFShift Type=Kinematic2025.1293.7
IQLShift Type=Kinematic2025.1290.1
DARAShift Type=Kinematic2025.1285.5
CQLShift Type=Kinematic2025.1283.8
MOREL2022.1062.6
MOReL2022.1062.6
MOReLModel category=Model-based2026.0562.6
MOPO2026.0262.4
EDAC-102026.0257.8
BRAC2022.1055.2
BRAC2022.1055.2
IQ-LearnProtocol=S-off-LfD, Trials=302023.0646.6
BOSAShift Type=Kinematic2025.1241.9
IQ-LearnProtocol=C-off-LfD, Trials=302023.0631.7
ORIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.0629.3
ValueDICEProtocol=S-off-LfD, Trials=302023.0628.2
ORIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.0614.5
FQLModel category=Model-free2026.0512.7
ORIL (TD3+BC)Protocol=S-off-LfO, Trials=302023.0612.2
ORIL (TD3+BC)Protocol=C-off-LfO, Trials=302023.0611.2
SQIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.068.8
ValueDICEProtocol=C-off-LfD, Trials=302023.068.3
SQIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.068
ADMModel category=Model-based2026.055.5
RAMBO2022.101.6
RAMBOModel category=Model-based2026.051.6