List your company

Offline Reinforcement Learning on D4RL Gym hopper-medium

104.8Normalized ReturnRORL
-3.46424.64352.7580.857Oct 4, 2021Jul 16, 2022Apr 27, 2023Feb 7, 2024Nov 18, 2024Aug 30, 2025Jun 12, 2026

Evaluation results

MethodLinks
RORLImplementation Source=Ours, Ensemble Size=102022.06104.8
SPQRBase algorithm=EDAC2024.01103.8
EDAC-10Implementation Source=Reproduced, Ensemble Size=102022.06103.6
SSCQL2025.10102.4
EDACImplementation=Ours2021.10101.6
EDACImplementation Source=Paper2022.06101.6
EDAC2024.01101.6
SAC-NImplementation=Ours2021.10100.3
SAC-Min2024.01100.3
SPQRBase algorithm=SAC-Min2024.01100.2
QIPO-OT2025.1094
GTP2025.1090.3
QIPO-Diff2025.1089.5
CQLImplementation=Original Paper2021.1086.6
CQL-Min2024.0186.6
IPDEvaluation Protocol=Tenfold Episode Evaluation2026.0381.6
MXQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1180.9
DDEvaluation Protocol=Tenfold Episode Evaluation2026.0379.3
QTEvaluation Protocol=Tenfold Episode Evaluation2026.0378
BRACImplementation=Reproduced2021.1077.8
QQLDomain=Gym Locomotion, Hyperparameter Tuning=consistent2025.1177.3
PBRL2022.0675.3
XQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1174.2
CQLEvaluation Protocol=Tenfold Episode Evaluation2026.0369.4
PDiTSeeds=52026.0668.2
DTEvaluation Protocol=Tenfold Episode Evaluation2026.0367.6
DRIVESeeds=52026.0667.3
QDTEvaluation Protocol=Tenfold Episode Evaluation2026.0366.5
IQLEvaluation Protocol=Tenfold Episode Evaluation2026.0366.3
IQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1166.3
IQLSeeds=52026.0666.3
EDTEvaluation Protocol=Tenfold Episode Evaluation2026.0364.5
DTSeeds=52026.0663.6
ReinformerEvaluation Protocol=Tenfold Episode Evaluation2026.0363.5
CQLImplementation=Reproduced2021.1061.9
CQL2022.0661.9
FQL2025.1060.6
BCSeeds=52026.0659.9
BCQImplementation=Reproduced2021.1059.4
TD3+BCDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1159.3
TD3+BCSeeds=52026.0659.3
CQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1158.5
CQLSeeds=52026.0658
BEARImplementation=Reproduced2021.1055.3
BCImplementation=Reproduced2021.1054.1
BC2022.0654.1
BC2024.0154.1
BCDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1152.9
MORELImplementation=Reproduced2021.1052.6
BEARSeeds=52026.0652.1
UWACImplementation=Reproduced2021.1046.2
SACImplementation=Reproduced2021.100.8
SAC-10Implementation Source=Reproduced, Ensemble Size=102022.060.8
REMImplementation=Reproduced2021.100.7