Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Objective Reinforcement Learning on mo-swimmer v5
Loading...
12,100
Hypervolume (HV)
Oracle
10,852
11,176
11,500
11,824
Feb 20, 2026
Hypervolume (HV)
Epsilon Multi-Objective (EUM)
Velocity of Optimality (VO)
Updated 4d ago
Evaluation Results
Method
Method
Links
Hypervolume (HV)
Epsilon Multi-Objective (EUM)
Velocity of Optimality (VO)
Oracle
Reward Sparsity=None (...
2026.02
12,100
9.41
4.22
PRISM
Reward Sparsity=Extrem...
2026.02
12,100
9.44
4.24
Baseline
Reward Sparsity=Extrem...
2026.02
10,900
4.1
1.58
Feedback
Search any
task
Search any
task
