Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on MuJoCo HumanoidStandup v4
Loading...
1.29
Normalized Performance
VDPO
0.874
0.982
1.09
1.198
May 23, 2024
Normalized Performance
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Performance
VDPO
Delays=5, Global steps=1M
2024.05
1.29
AD-SAC
Delays=5, Global steps=1M
2024.05
1.22
DC/AC
Delays=5, Global steps=1M
2024.05
1.16
AD-SAC
Delays=25, Global step...
2024.05
1.15
BPQL
Delays=5, Global steps=1M
2024.05
1.13
VDPO
Delays=25, Global step...
2024.05
1.13
AD-SAC
Delays=50, Global step...
2024.05
1.12
BPQL
Delays=25, Global step...
2024.05
1.09
BPQL
Delays=50, Global step...
2024.05
1.06
VDPO
Delays=50, Global step...
2024.05
1.04
DC/AC
Delays=25, Global step...
2024.05
1.03
A-SAC
Delays=5, Global steps=1M
2024.05
1.02
DC/AC
Delays=50, Global step...
2024.05
1.02
DIDA
Delays=5, Global steps=1M
2024.05
1
A-SAC
Delays=25, Global step...
2024.05
0.97
DIDA
Delays=25, Global step...
2024.05
0.97
A-SAC
Delays=50, Global step...
2024.05
0.9
DIDA
Delays=50, Global step...
2024.05
0.89
Feedback
Search any
task
Search any
task
