Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on MuJoCo Humanoid
Loading...
6,969.74
Average Reward
CrossQ+FEMA
660.0288
2,298.1269
3,936.225
5,574.3231
Feb 7, 2021
Dec 13, 2021
Oct 18, 2022
Aug 23, 2023
Jun 27, 2024
May 2, 2025
Mar 7, 2026
Average Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Reward
CrossQ+FEMA
integration=FEMA
2026.03
6,969.74
CrossQ
2026.03
6,267.3
TOP-TD3
Training steps=1M, Num...
2021.02
5,899
ND TOP-TD3
Training steps=1M, Num...
2021.02
5,445
SAC+FEMA
integration=FEMA
2026.03
5,429.08
TD3
Training steps=1M, Num...
2021.02
5,386
OAC
Training steps=1M, Num...
2021.02
5,349
SAC
Training steps=1M, Num...
2021.02
5,315
SAC
2026.03
5,290.8
QR-TD3
Training steps=1M, Num...
2021.02
5,003
EMAC
2026.03
3,808.84
PPO+FEMA
integration=FEMA
2026.03
1,102.82
PPO
2026.03
902.71
Feedback
Search any
task
Search any
task