List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper medium-expert

114Normalized ScoreQ-ALIGN DT
6.04834.07462.190.126Dec 2, 2025Dec 31, 2025Jan 29, 2026Feb 28, 2026Mar 29, 2026Apr 27, 2026May 27, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Q-ALIGN DT2026.05114
QT2026.05113.4
DM2026.05111.8
LSDT2026.05111.7
TD3-CVAE2026.02111.6
O-DICE2026.02110.8
DMG2026.02110.4
DC2026.05110.4
RADT2026.05110.4
QCS2026.05110.2
SAC-RND2026.02109.8
GPC-SAC2026.02109.8
DT2026.05107.6
CGDT2026.05107.6
I-TAPNoise=1.252026.02106.91
CQL2026.02105.6
Anti-exploration Method2026.02102.9
TD3+BC2026.0598
L-MAPNoise=1.252026.0294.65
IQL2026.0291.5
IQL2026.0591.5
DTNoise=1.252026.0287.41
I-TAPNoise=3.752026.0285.07
L-MAPNoise=3.752026.0280.51
I-TAPNoise=7.52026.0270.43
DTNoise=3.752026.0264.97
L-MAPNoise=7.52026.0262.9
DTNoise=7.52026.0258.96
DVDF-IGDF2025.1243.2
IQL2025.1238.3
DVDF-OTDF2025.1237.4
IGDF2025.1236.3
OTDF2025.1231.6
DARA2025.1219.7
BOSA2025.1210.2