Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Objective Reinforcement Learning on mo-walker2d v5
Loading...
47,700
Hypervolume (HV)
PRISM
32,828
36,689
40,550
44,411
Feb 20, 2026
Hypervolume (HV)
Epsilon-Maximization (EUM)
Vector Dominance (VO)
Updated 4d ago
Evaluation Results
Method
Method
Links
Hypervolume (HV)
Epsilon-Maximization (EUM)
Vector Dominance (VO)
PRISM
Reward Sparsity=Extrem...
2026.02
47,700
120.43
59.35
Oracle
Reward Sparsity=None (...
2026.02
42,100
107.58
53.22
Baseline
Reward Sparsity=Extrem...
2026.02
33,400
82.13
39.18
Feedback
Search any
task
Search any
task
