Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Circle (offline)
Loading...
1.27
Normalized Reward
Task-Only
0.8852
0.9851
1.085
1.1849
May 20, 2026
Normalized Reward
Normalized Cost
Updated 12d ago
Evaluation Results
Method
Method
Links
Normalized Reward
Normalized Cost
Task-Only
Algorithm=Task-Only
2026.05
1.27
1
RC
Algorithm=Reward Combi...
2026.05
1.09
0
SOPL
Algorithm=Safety-Only...
2026.05
1.04
0
Oracle
Algorithm=Oracle
2026.05
1
0
Safe-CPL
Algorithm=Safe-CPL
2026.05
0.91
0
Safe-VPL
Algorithm=Safe-VPL
2026.05
0.9
0
Feedback
Search any
task
Search any
task
