ResearchBenchmarksContinuous Control on MuJoCo Walker2d (UT, HV, ED)Continuous Control on MuJoCo Walker2d (UT, HV, ED)Follow0.05Uncertainty Time (UT)MORL/D-0.02480.48010.9851.4899Apr 27, 2026Evaluation resultsMethodMethodLinksUncertainty Time (UT)Hindsight Value (HV)Endpoint Distance (ED)MORL/D2026.040.050.350.03PCN2026.040.10.170.03FB2026.040.291.970SFOLS2026.040.411.220.15GPI-PD2026.040.541.130.15PGMORL2026.041.153.520.18CAPQL2026.041.490.030Q-Pensieve2026.041.664.540.36PD-MORLw/o interpolator=truew/o interpolator=true2026.041.74.020.27MORL-FB2026.041.874.56—GPI-LS2026.041.923.350.32