List your company

Locomotion on MuJoCo Walker2d Medium-Replay D4RL

128.6Average Normalized ScoreCPQL→PQL
66.09682.32398.55114.777Mar 3, 2026Mar 15, 2026Mar 27, 2026Apr 8, 2026Apr 20, 2026May 2, 2026May 14, 2026

Evaluation results

MethodLinks
CPQL→PQLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05128.6
RLPDEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05119
CQL→SACEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05114.7
Cal-QLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0598.4
CPQLsetting=offline2026.0597.4
PEXEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0587.2
SAGE2026.0385.3
DVreproduced=true2026.0384.1
X-QLsetting=offline2026.0582.2
SQLsetting=offline2026.0581.2
LoMAP2026.0378.7
RGG2026.0378.3
EQLsetting=offline2026.0576.6
Diffuserreproduced=true2026.0370.6
InACsetting=offline2026.0569.8
LDCQ2026.0368.5