List your company

Offline Reinforcement Learning on D4RL hopper-random

53.6Normalized ScoreMOREL
-1.20813.02127.2541.479Feb 16, 2021Dec 30, 2021Nov 13, 2022Sep 27, 2023Aug 10, 2024Jun 24, 2025May 8, 2026

Evaluation results

MethodLinks
MOREL2021.1053.6
MOREL2021.0253.6
MOReLNumber of random seeds=42026.0338.1
MOReL2026.0538.1
RRPINumber of random seeds=42026.0335
PMDBNumber of random seeds=42026.0332.7
AMGNumber of random seeds=42026.0332.7
PMDBMethod Type=Model-based2023.1032.7
PMDB2026.0532.7
ADM2026.0532.7
EPQNumber of random seeds=42026.0332.1
EPQ2026.0532.1
PSPOAveraged across=4 random seeds2026.0531.9
CROPMethod Type=Model-based2023.1031.8
Repb-SDE2021.1031.7
Repb-SDEalgorithm class=model-based2021.1031.7
BEAR2021.1031.4
CQLalgorithm class=model-free2021.1031.4
SAC-NImplementation=Ours2021.1031.3
Count-MORLMethod Type=Model-based2023.1030.7
ROMI-CQL2021.1030.2
ROMI-CQLbase algorithm=CQL2021.1030.2
RAMBONumber of random seeds=42026.0325.4
RAMBO2026.0525.4
EDACImplementation=Ours2021.1025.3
EDACMethod Type=Model-free2023.1025.3
DMGNumber of random seeds=42026.0320.4
DMG2026.0520.4
ProposedSeeds=52023.1018.7
COMBOSeeds=52023.1017.9
COMBO2021.1017.9
COMBO2021.0217.9
ATACSeeds=52023.1017.5
ATACMethod Type=Model-free2023.1017.5
Fu et al.Algorithmic Template=Iterative2021.0612.2
BRAC-v2021.0212.2
CABI+TD3-BCMethod Type=Model-based2023.1011.9
MOPO2021.0211.7
RAMBOMethod Type=Model-based2023.1011.5
BEARSeeds=52023.1011.4
Fisher-BRCimplementation=author-provided (re-run)2021.0611.4
BEAR2021.0211.4
SAC-off2021.0211.3
OptiDICESeeds=52023.1011.2
TD3+BCSeeds=52023.1011.1
BRAC-pimplementation=reported2021.0611.1
TD3+BCalpha=2.52021.0611
BRAC-p2021.0211
IQLSeeds=52023.1010.8
CQLImplementation=Original Paper2021.1010.8
CQL2021.0210.8
CQLSeeds=52023.1010.7
CQLimplementation=author-provided (re-run)2021.0610.7
BCQSeeds=52023.1010.6
BRAC-P2021.1010
SACImplementation=Reproduced2021.109.9
AWACimplementation=reported2021.069.6
BCimplementation=own2021.069.5
BRACImplementation=Reproduced2021.108.1
ROMI-BCQ2021.108
BAIL2021.108
BCQ2021.107.9
BCQImplementation=Reproduced2021.107.8
Rev. KL Reg.Algorithmic Template=One-step2021.067.8
BRAC-v2021.107.1
COMBOMethod Type=Model-based2023.107
BooT-oGeneration Strategy=Autoregressive2022.066.8
CQL2021.106.7
Easy BCQAlgorithmic Template=One-step2021.066.7
TT2022.066.7
BooT-rGeneration Strategy=Teacher-forcing2022.066.6
BooT-rGeneration Strategy=Autoregressive2022.066.5
BooT-oGeneration Strategy=Teacher-forcing2022.066.5
Exp. WeightAlgorithmic Template=One-step2021.065.6
CQLImplementation=Reproduced2021.105.3
CQLNumber of random seeds=42026.035.3
CQL2026.055.3
MOPO2021.104.1
BCImplementation=Reproduced2021.103.7
BEARImplementation=Reproduced2021.103.6
REMImplementation=Reproduced2021.103.4
UWACImplementation=Reproduced2021.102.6
BCAlgorithmic Template=One-step2021.062.6
BC2021.021.6
BC2021.100.9
BC2021.100.9