Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safe Reinforcement Learning on AntButton (test)
Loading...
0
Violation Rate
TD3ADRC
-24.88
143.06
311
478.94
Jan 26, 2026
Violation Rate
Magnitude
Average Cost
Updated 4d ago
Evaluation Results
Method
Method
Links
Violation Rate
Magnitude
Average Cost
TD3ADRC
Base Algorithm=TD3, La...
2026.01
0
0
0.86
TRPOADRC
Base Algorithm=TRPO, L...
2026.01
0
0
4.15
CPPOADRC
Base Algorithm=CPPO, L...
2026.01
1
0
2.69
TRPOLag
Base Algorithm=TRPO, L...
2026.01
1
0
4.4
TRPOPID
Base Algorithm=TRPO, L...
2026.01
1
0
4.29
CPPOLag
Base Algorithm=CPPO, L...
2026.01
22
0.83
6.09
CPPOPID
Base Algorithm=CPPO, L...
2026.01
30
0.01
6.95
DDPGADRC
Base Algorithm=DDPG, L...
2026.01
193
0.12
4.87
TD3PID
Base Algorithm=TD3, La...
2026.01
224
0.11
3.14
TD3Lag
Base Algorithm=TD3, La...
2026.01
331
0.32
6.22
DDPGLag
Base Algorithm=DDPG, L...
2026.01
572
0.3
7.35
DDPGPID
Base Algorithm=DDPG, L...
2026.01
622
0.47
7.92
Feedback
Search any
task
Search any
task