List your company

Offline Reinforcement Learning on halfcheetah medium-replay

68.4Normalized ScoreLAWM
5.37621.73838.154.462Oct 10, 2023Mar 18, 2024Aug 25, 2024Feb 1, 2025Jul 11, 2025Dec 18, 2025May 27, 2026

Evaluation results

MethodLinks
LAWMaction-conditioned data percentage=5%2025.1268.4
C-LAPaction-conditioned data percentage=100%, variant=Oracle2025.1265
Anti-exploration Method2026.0262
Q-ALIGN DT2026.0557.1
GPC-SAC2026.0255.7
COMBOSeeds=52023.1055.1
SAC-RND2026.0254.9
QCS2026.0554.1
TD3+BCaction-conditioned data percentage=100%, variant=Oracle2025.1253.9
DMG2026.0251.4
ProposedSeeds=52023.1049.3
QT2026.0548.9
TD3+BCSeeds=52023.1048.3
ATACSeeds=52023.1048
IDM-TD3+BCaction-conditioned data percentage=5%2025.1246.6
CQLReward Specification=Step-wise2024.0246.2
CQL2026.0245.5
TD3-CVAE2026.0245.3
TD3+BC2026.0544.6
IQLSeeds=52023.1044.2
IQL2026.0244.2
IQL2026.0544.1
O-DICE2026.0244
LSDT2026.0542.9
CQLSeeds=52023.1041.9
DC2026.0541.3
RADT2026.0541.3
CGDT2026.0540.4
OptiDICESeeds=52023.1039.8
DM2026.0539.6
BEARSeeds=52023.1038.6
BCQSeeds=52023.1038.2
DT2026.0536.6
QDTReward Specification=Step-wise2024.0235.6
C-LAPaction-conditioned data percentage=5%2025.1234.6
DTReward Specification=Step-wise2024.0234.1
DTReward Specification=Final Return2024.0233
QDTReward Specification=Final Return2024.0232.8
STCDynamics Shift=Gravity, Target Quality=medium2026.0226.7
DVDF-OTDF2025.1225.1
OTDFDynamics Shift=Gravity, Target Quality=medium2026.0221.5
IQLDynamics Shift=Gravity, Target Quality=medium2026.0220.1
BOSADynamics Shift=Gravity, Target Quality=medium2026.0220
DVDF-IGDF2025.1219.4
OTDF2025.1217.9
DARADynamics Shift=Gravity, Target Quality=medium2026.0217.6
SRPODynamics Shift=Gravity, Target Quality=medium2026.0217.5
IGDF2025.1214.8
IGDFDynamics Shift=Gravity, Target Quality=medium2026.0214.4
TD3+BCaction-conditioned data percentage=5%2025.1214
IQL2025.1212.5
BOSA2025.129.5
DARA2025.128.6
CQLReward Specification=Final Return2024.027.8