ResearchBenchmarksContinuous Control on MuJoCo Humanoid5dFollow1.11Undiscounted Return (UT)MORL-FB-0.14840.17830.5050.8317Apr 27, 2026Evaluation ResultsMethodMethodLinksUndiscounted Return (UT)Hindsight Value (HV)Endpoint Distance (ED)MORL-FB2026.041.116.99—GPI-LS2026.040.723.480.09MORL/D2026.040.580.310.08FB2026.040.554.690.03PGMORL2026.040.540.590.1SFOLS2026.040.542.150.05PD-MORLw/o interpolator=truew/o interpolator=true2026.040.383.910.03GPI-PD2026.040.30.20.03Q-Pensieve2026.040.121.80CAPQL2026.040.0800.04PCN2026.04-0.100