List your company

Continuous Control on MuJoCo Humanoid

6,969.74Average RewardCrossQ+FEMA
660.02882,298.12693,936.2255,574.3231Feb 7, 2021Dec 13, 2021Oct 18, 2022Aug 23, 2023Jun 27, 2024May 2, 2025Mar 7, 2026

Evaluation results

MethodLinks
CrossQ+FEMAintegration=FEMA2026.036,969.74
CrossQ2026.036,267.3
TOP-TD3Training steps=1M, Number of trials=102021.025,899
ND TOP-TD3Training steps=1M, Number of trials=102021.025,445
SAC+FEMAintegration=FEMA2026.035,429.08
TD3Training steps=1M, Number of trials=102021.025,386
OACTraining steps=1M, Number of trials=102021.025,349
SACTraining steps=1M, Number of trials=102021.025,315
SAC2026.035,290.8
QR-TD3Training steps=1M, Number of trials=102021.025,003
EMAC2026.033,808.84
PPO+FEMAintegration=FEMA2026.031,102.82
PPO2026.03902.71