List your company

Offline-to-Online RL on D4RL MuJoCo (Medium and Random Configurations)

54.5HalfCheetah (M) ScoreCal-QL
28.535.254248.75Jul 1, 2026

Evaluation results

MethodLinks
Cal-QL2026.0754.5—74.487.413.111.91142
AWAC2026.0752.2—81.986.432.918.14.245.9
OPT2026.0748.5—105.594.637.514.9951.7
Hard-Switch2026.0748.2—101.299.2435574.770.2
Loss Smoothing2026.0748.2—99.9103.145.277.96873.7
Offline2026.0747.3—47.283.28.313.57.234.5
Online2026.0729.5—69.661.518.467.273.353.2