Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safe Reinforcement Learning on Swimmer Velocity tasks suite
Loading...
36.32
Average Reward
ADRC
28.416
30.468
32.52
34.572
Jan 26, 2026
Average Reward
Average Cost
Violation Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Reward
Average Cost
Violation Rate
ADRC
Base RL Algorithm=TRPO
2026.01
36.32
19.03
12.16
PID
Base RL Algorithm=CPPO
2026.01
30.1
22.44
28.02
ADRC
Base RL Algorithm=CPPO
2026.01
29.39
16.77
14.16
PID
Base RL Algorithm=TRPO
2026.01
28.72
21.34
37.85
Feedback
Search any
task
Search any
task
