Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-objective Reinforcement Learning on MuJoCo 8 continuous-action tasks MO-Gymnasium (aggregated)
Loading...
3.25
Hypervolume (HV)
PDMORL
1.17
1.71
2.25
2.79
May 9, 2026
Hypervolume (HV)
Expected Utility Maximization (EUM)
Scalarized Performance (SP)
Updated 22d ago
Evaluation Results
Method
Method
Links
Hypervolume (HV)
Expected Utility Maximization (EUM)
Scalarized Performance (SP)
PDMORL
Method Type=Model-Free...
2026.05
3.25
3.25
3.62
GPI-PD
Method Type=Model-Base...
2026.05
3
3
2.25
CAPQL-MF
Method Type=Model-Free...
2026.05
2.75
2.62
1.75
COLA
Method Type=Model-Free...
2026.05
2
2
2.12
PCSAC-MF
Method Type=Model-Free...
2026.05
2
2.12
2.5
CAPQL-MB
Method Type=Model-Base...
2026.05
1.75
1.75
2
PCSAC-MB
Method Type=Model-Base...
2026.05
1.25
1.25
1.75
Feedback
Search any
task
Search any
task
