Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Bullet Safety Gym CarRun
Loading...
577.7
Reward
PPO-Lagrangian
550.972
557.911
564.85
571.789
Apr 17, 2025
Reward
Cost
Labeled Trajectories
Updated 25d ago
Evaluation Results
Method
Method
Links
Reward
Cost
Labeled Trajectories
PPO-Lagrangian
Knowledge Level=Oracle
2025.04
577.7
22
-
FOCOPS
Knowledge Level=Oracle
2025.04
573.7
44.9
-
C-T Baseline
Knowledge Level=Zero K...
2025.04
569.1
13.3
6,000
TraCeS
Knowledge Level=Zero K...
2025.04
568.3
23.3
8,832
TraCeS
Knowledge Level=Zero K...
2025.04
568.3
23.3
8,832
CPPO-PID
Knowledge Level=Oracle
2025.04
568.2
14.8
-
CUP
Knowledge Level=Oracle
2025.04
567.8
6.9
-
TRPO-Saute
Knowledge Level=Oracle
2025.04
552
22.4
-
Feedback
Search any
task
Search any
task