List your company

Offline Reinforcement Learning on D4RL halfcheetah-random

45.4Normalized ScoreADMPO
-2.6489.82622.334.774Jun 12, 2021Apr 6, 2022Jan 30, 2023Nov 24, 2023Sep 18, 2024Jul 13, 2025May 8, 2026

Evaluation results

MethodLinks
ADMPOMethod Category=Conservative model-based2025.1245.4
AMGNumber of random seeds=42026.0345.4
ADM2026.0545.4
VIPOMethod Category=Conservative model-based2025.1242.5
MAPLEMethod Category=Bayesian-inspired2025.1241.5
Count-MORLMethod Type=Model-based2023.1041
RAMBOMethod Category=Model-free2025.1240
RAMBOMethod Type=Model-based2023.1040
MoMoMethod Category=Conservative model-based2025.1239.6
RAMBONumber of random seeds=42026.0339.5
RAMBO2026.0539.5
MOBILEMethod Category=Conservative model-based2025.1239.3
MORELImplementation=Reproduced2021.1038.9
MOReLNumber of random seeds=42026.0338.9
MOReL2026.0538.9
COMBOSeeds=52023.1038.8
COMBO2021.1038.8
COMBOalgorithm class=model-based2021.1038.8
COMBOMethod Category=Model-free2025.1238.8
COMBOMethod Type=Model-based2023.1038.8
MOPOMethod Category=Conservative model-based2025.1238.5
PMDBNumber of random seeds=42026.0337.8
PMDBMethod Type=Model-based2023.1037.8
PMDB2026.0537.8
PSPOAveraged across=4 random seeds2026.0537.7
ProposedSeeds=52023.1037.6
NEUBAYMethod Category=Ours2025.1237
MoDAPMethod Category=Bayesian-inspired2025.1236.5
RRPINumber of random seeds=42026.0335.5
CQLImplementation=Original Paper2021.1035.4
MOPO2021.1035.4
Fu et al.Algorithmic Template=Iterative2021.0635.4
SUMOMethod Category=Conservative model-based2025.1234.9
CROPMethod Type=Model-based2023.1033.7
EPQNumber of random seeds=42026.0333
EPQ2026.0533
CBOPMethod Category=Bayesian-inspired2025.1232.8
Fisher-BRCimplementation=author-provided (re-run)2021.0632.2
CQLImplementation=Reproduced2021.1031.3
CQLMethod Category=Model-free2025.1231.3
CQLNumber of random seeds=42026.0331.3
CQL2026.0531.3
LEQMethod Category=Conservative model-based2025.1230.8
APE-VMethod Category=Conservative model-based2025.1229.9
SACImplementation=Reproduced2021.1029.7
Repb-SDE2021.1029.1
DMGNumber of random seeds=42026.0328.8
DMG2026.0528.8
EDACImplementation=Ours2021.1028.4
EDACMethod Category=Model-free2025.1228.4
EDACMethod Type=Model-free2023.1028.4
SAC-NImplementation=Ours2021.1028
CQLSeeds=52023.1026.7
TD3+BCSeeds=52023.1026.1
MOREL2021.1025.6
BEARSeeds=52023.1025.1
ROMI-CQL2021.1024.5
ROMI-CQLbase algorithm=CQL2021.1024.5
BRACImplementation=Reproduced2021.1024.3
BRAC-pimplementation=reported2021.0623.5
IQLSeeds=52023.1022.4
CQLimplementation=author-provided (re-run)2021.0621.7
CQL2021.1019.6
CQLalgorithm class=model-free2021.1019.6
CABI+TD3-BCMethod Type=Model-based2023.1015.1
BEARImplementation=Reproduced2021.1012.6
OptiDICESeeds=52023.1011.6
TD3+BCalpha=2.52021.0610.2
TT2022.067.9
BooT-rGeneration Strategy=Teacher-forcing2022.067.5
Rev. KL Reg.Algorithmic Template=One-step2021.066.9
BooT-rGeneration Strategy=Autoregressive2022.066.9
BooT-oGeneration Strategy=Autoregressive2022.066.7
Easy BCQAlgorithmic Template=One-step2021.065.4
BooT-oGeneration Strategy=Teacher-forcing2022.064.6
ATACSeeds=52023.103.9
ATACMethod Type=Model-free2023.103.9
Exp. WeightAlgorithmic Template=One-step2021.063.7
UWACImplementation=Reproduced2021.102.3
ROMI-BCQ2021.102.3
BCQ2021.102.3
BEAR2021.102.3
BCQSeeds=52023.102.2
BCImplementation=Reproduced2021.102.2
BCQImplementation=Reproduced2021.102.2
BC2021.102.2
BRAC-P2021.102.2
BRAC-v2021.102.2
BAIL2021.102.2
AWACimplementation=reported2021.062.2
BCAlgorithmic Template=One-step2021.062.2
BCimplementation=own2021.062
BC2021.10-0.1
REMImplementation=Reproduced2021.10-0.8