Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on HalfCheetah vel (offline)
Loading...
1.85
Normalized Reward
Task-Only
0.3836
0.7643
1.145
1.5257
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
1.85
1
Oracle
Algorithm=Oracle
2026.05
1
0
Safe-VPL
Algorithm=Safe-VPL
2026.05
0.96
0.004
SOPL
Algorithm=Safety-Only...
2026.05
0.93
0.014
Safe-CPL
Algorithm=Safe-CPL
2026.05
0.92
0.018
RC
Algorithm=Reward Combi...
2026.05
0.44
0.107
Feedback
Search any
task
Search any
task
