Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Objective Reinforcement Learning on mo-hopper v5
Loading...
15,800,000
Hypervolume (x10^7)
PRISM
8,104,000
10,102,000
12,100,000
14,098,000
Feb 20, 2026
Hypervolume (x10^7)
EUM
VO
Updated 4d ago
Evaluation Results
Method
Method
Links
Hypervolume (x10^7)
EUM
VO
PRISM
Reward Sparsity=Extrem...
2026.02
15,800,000
147.43
66.66
Oracle
Reward Sparsity=None (...
2026.02
13,000,000
129.04
59.07
Baseline
Reward Sparsity=Extrem...
2026.02
8,400,000
97.64
43.36
Feedback
Search any
task
Search any
task
