Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Constrained Reinforcement Learning on AntCircle
Loading...
198.6
Episodic Reward
e-COP
124.24
143.545
162.85
182.155
Dec 11, 2025
Episodic Reward
Episodic Cost
Updated 4d ago
Evaluation Results
Method
Method
Links
Episodic Reward
Episodic Cost
e-COP
Cost Threshold=10, Num...
2025.12
198.6
9.8
P3O
Cost Threshold=10, Num...
2025.12
182.6
9.8
PCPO
Cost Threshold=10, Num...
2025.12
168.3
9.5
FOCOPS
Cost Threshold=10, Num...
2025.12
161.9
9.9
APPO
Cost Threshold=10, Num...
2025.12
155.5
10
IPO
Cost Threshold=10, Num...
2025.12
149.3
9.5
PPO-L
Cost Threshold=10, Num...
2025.12
134.4
9.6
CPO
Cost Threshold=10, Num...
2025.12
127.1
10.1
Feedback
Search any
task
Search any
task
