List your company

Offline Reinforcement Learning on walker2d medium

1,248Normalized ScoreQDFM
-68.64273.18615956.82Oct 10, 2023Mar 18, 2024Aug 25, 2024Feb 1, 2025Jul 11, 2025Dec 18, 2025May 27, 2026

Evaluation results

MethodLinks
QDFM2026.021,248
BCQ2026.02930
CQL2026.02665
GreedyQ2026.02659
AWBC2026.02248
Q-ALIGN DT2026.0594.7
DMG2026.0292.4
SAC-RND2026.0291.6
LAWMaction-conditioned data percentage=5%2025.1291.4
ATACSeeds=52023.1089.6
Anti-exploration Method2026.0289.3
QT2026.0588.8
QCS2026.0588.2
GPC-SAC2026.0287.6
O-DICE2026.0284.9
DM2026.0583.8
TD3+BC2026.0583.7
COMBOSeeds=52023.1081.9
TD3+BCSeeds=52023.1081.7
LSDT2026.0581
ProposedSeeds=52023.1080.8
IQL2026.0579.9
CQLReward Specification=Step-wise2024.0279.2
DC2026.0579.2
CGDT2026.0579.1
IQLSeeds=52023.1078.3
IQL2026.0278.3
CQLSeeds=52023.1077.2
I-TAPNoise=3.52026.0276.56
L-MAPNoise=3.52026.0275.77
DT2026.0574
DTReward Specification=Step-wise2024.0273.3
CQL2026.0273.3
TD3+BCaction-conditioned data percentage=100%, variant=Oracle2025.1271.5
C-LAPaction-conditioned data percentage=100%, variant=Oracle2025.1271.1
DTReward Specification=Final Return2024.0269.9
C-LAPaction-conditioned data percentage=5%2025.1268.7
TD3-CVAE2026.0268.2
QDTReward Specification=Step-wise2024.0267.1
TD3+BCaction-conditioned data percentage=5%2025.1264.7
IDM-TD3+BCaction-conditioned data percentage=5%2025.1264.3
QDTReward Specification=Final Return2024.0263.7
I-TAPNoise=9.52026.0260.22
BEARSeeds=52023.1059.1
L-MAPNoise=9.52026.0255.96
I-TAPNoise=152026.0254.6
BCQSeeds=52023.1053.1
DTNoise=3.52026.0251.89
L-MAPNoise=152026.0250.1
DTNoise=9.52026.0239.16
DTNoise=152026.0230.69
DVDF-IGDF2025.1224.3
DVDF-OTDF2025.1223.7
OptiDICESeeds=52023.1021.8
OTDF2025.1219.3
IQL2025.1216.4
DARA2025.1215.8
IGDF2025.1214.3
BOSA2025.1210.6
CQLReward Specification=Final Return2024.020
AWAC2026.02-18