List your company

Offline Reinforcement Learning on D4RL Gym walker2d (medium-replay)

109.7Normalized ReturnROMI-CQL
-6.88423.38353.6583.917Oct 1, 2021Jun 27, 2022Mar 23, 2023Dec 17, 2023Sep 11, 2024Jun 7, 2025Mar 4, 2026

Evaluation results

MethodLinks
ROMI-CQL2021.10109.7
ROMI-CQLbase algorithm=CQL2021.10109.7
IPDEvaluation Protocol=Tenfold Episode Evaluation2026.0396.2
QTEvaluation Protocol=Tenfold Episode Evaluation2026.0394.2
GTP2025.1094.2
EDAC-10Implementation Source=Reproduced, Ensemble Size=102022.0694
TT(+Q)Configuration=Trifle2023.1090.6
RORLImplementation Source=Ours, Ensemble Size=102022.0690.4
QQLDomain=Gym Locomotion, Hyperparameter Tuning=consistent2025.1190.2
QIPO-Diff2025.1090.1
SAC-10Implementation Source=Reproduced, Ensemble Size=102022.0689.6
SPQRBase algorithm=EDAC2024.0189.6
CQLalgorithm class=model-free2021.1088.4
TTConfiguration=Trifle2023.1088.3
CQL2021.1088.2
SPQRBase algorithm=SAC-Min2024.0187.8
EDACImplementation=Ours2021.1087.1
EDACImplementation Source=Paper2022.0687.1
EDAC2024.0187.1
SSCQL2025.1085.9
TT(+Q)Configuration=base2023.1084.6
Repb-SDE2021.1083.8
Repb-SDEalgorithm class=model-based2021.1083.8
MXQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1183.6
TTConfiguration=base2023.1082.6
XQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1182.2
TD3(+BC)2023.1081.8
TD3+BCDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1181.8
DTEvaluation Protocol=Tenfold Episode Evaluation2026.0379.4
SAC-NImplementation=Ours2021.1078.7
SAC-Min2024.0178.7
QIPO-OT2025.1078.6
PBRL2022.0677.7
CQL2023.1077.2
CQLEvaluation Protocol=Tenfold Episode Evaluation2026.0377.2
CQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1177.2
CQLImplementation=Reproduced2021.1076.8
CQL2022.0676.8
DD2023.1075
EDTEvaluation Protocol=Tenfold Episode Evaluation2026.0374.8
IQL2023.1073.9
IQLEvaluation Protocol=Tenfold Episode Evaluation2026.0373.9
IQLDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1173.9
DTConfiguration=Trifle2023.1073.5
ReinformerEvaluation Protocol=Tenfold Episode Evaluation2026.0372.9
MOPO2021.1069.4
DDEvaluation Protocol=Tenfold Episode Evaluation2026.0368.9
DTConfiguration=base2023.1066.6
%BC2023.1062.5
QDTEvaluation Protocol=Tenfold Episode Evaluation2026.0358.2
COMBO2021.1056
BAIL2021.1051.4
MOREL2021.1049.8
ROMI-BCQ2021.1049.5
BRACImplementation=Reproduced2021.1047.9
BCQ2021.1041.8
FQL2025.1038.8
CQL-Min2024.0132.6
UWACImplementation=Reproduced2021.1027.1
BCDomain=Gym Locomotion, Hyperparameter Tuning=individually tuned2025.1126
BCImplementation=Reproduced2021.1020.3
BC2022.0620.3
BC2024.0120.3
BCQImplementation=Reproduced2021.1012.5
MORELImplementation=Reproduced2021.1012.2
BEARImplementation=Reproduced2021.109.3
BRAC-v2021.104.3
BC2021.102.2
BC2021.102.2
REMImplementation=Reproduced2021.101.9
BRAC-P2021.101.7
SACImplementation=Reproduced2021.10-0.4
BEAR2021.10-2.4