List your company

Offline Reinforcement Learning on halfcheetah medium

68.2Normalized ScoreAnti-exploration Method
-3.331215.239433.8152.3806Oct 10, 2023Mar 18, 2024Aug 25, 2024Feb 1, 2025Jul 11, 2025Dec 18, 2025May 27, 2026

Evaluation results

MethodLinks
Anti-exploration Method2026.0268.2
SAC-RND2026.0266.6
Q-ALIGN DT2026.0565.3
GPC-SAC2026.0260.8
QCS2026.0559
ProposedSeeds=52023.1058.1
DMG2026.0254.9
COMBOSeeds=52023.1054.2
ATACSeeds=52023.1053.3
QT2026.0551.4
TD3+BC2026.0548.3
IQLSeeds=52023.1047.4
O-DICE2026.0247.4
IQL2026.0247.4
IQL2026.0547.4
CQL2026.0247
CQLReward Specification=Step-wise2024.0244.4
LSDT2026.0543.6
DM2026.0543.5
TD3-CVAE2026.0243.2
CGDT2026.0543
DC2026.0543
DT2026.0542.6
DTReward Specification=Final Return2024.0242.4
QDTReward Specification=Final Return2024.0242.4
STCDynamics Shift=Gravity, Target Quality=medium2026.0242.4
QDTReward Specification=Step-wise2024.0242.3
DTReward Specification=Step-wise2024.0242.1
BEARSeeds=52023.1041.7
DARADynamics Shift=Gravity, Target Quality=medium2026.0241.2
BCQSeeds=52023.1040.7
OTDFDynamics Shift=Gravity, Target Quality=medium2026.0240.7
IQLDynamics Shift=Gravity, Target Quality=medium2026.0239.6
BOSADynamics Shift=Gravity, Target Quality=medium2026.0238.9
OptiDICESeeds=52023.1038.2
CQLSeeds=52023.1037.2
SRPODynamics Shift=Gravity, Target Quality=medium2026.0236.9
IGDFDynamics Shift=Gravity, Target Quality=medium2026.0236.6
TD3+BCSeeds=52023.1027.8
DVDF-IGDF2025.1226.7
OTDF2025.1224.6
DVDF-OTDF2025.1222.9
IGDF2025.1222.6
BCQ2026.0220.23
AWAC2026.0219.69
IQL2025.1218.7
BOSA2025.1217.3
DARA2025.1216.1
QDFM2026.024.92
AWBC2026.022.22
CQLReward Specification=Final Return2024.021
GreedyQ2026.02-0.23
CQL2026.02-0.58