Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Constrained Reinforcement Learning on Safety Gymnasium PointCircle2 (eval)
Loading...
41.2
Reward
CUP
38.912
39.506
40.1
40.694
Apr 17, 2025
Reward
Cost
Labeled Trajectories
Updated 24d ago
Evaluation Results
Method
Method
Links
Reward
Cost
Labeled Trajectories
CUP
Knowledge Level=Oracle
2025.04
41.2
31.8
-
TraCeS
Knowledge Level=Zero K...
2025.04
41.1
19.8
5,465
TRPO-Saute
Knowledge Level=Oracle
2025.04
39.5
3.7
-
FOCOPS
Knowledge Level=Oracle
2025.04
39
12.9
-
Feedback
Search any
task
Search any
task