List your company

Locomotion on MuJoCo halfcheetah-medium-replay

95.8Normalized ScoreCPQL→PQL
42.2456.14570.0583.955May 14, 2026

Evaluation results

MethodLinks
CPQL→PQLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0595.8
CQL→SACEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0594.8
RLPDEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0590.1
Cal-QLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0562.1
CPQLsetting=offline2026.0560.3
PEXEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.0555.4
X-QLsetting=offline2026.0545.2
SQLsetting=offline2026.0544.8
EQLsetting=offline2026.0544.5
InACsetting=offline2026.0544.3