Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Bullet Safety Gym AntRun
Loading...
684.8
Reward
FOCOPS
586.728
612.189
637.65
663.111
Apr 17, 2025
Reward
Cost
Labeled Trajectories
Updated 25d ago
Evaluation Results
Method
Method
Links
Reward
Cost
Labeled Trajectories
FOCOPS
Knowledge Level=Oracle
2025.04
684.8
23.3
-
PPO-Lagrangian
Knowledge Level=Oracle
2025.04
683.7
25.4
-
CPPO-PID
Knowledge Level=Oracle
2025.04
675.5
22.6
-
C-T Baseline
Knowledge Level=Zero K...
2025.04
654.6
33.3
6,000
TRPO-Saute
Knowledge Level=Oracle
2025.04
652
13.8
-
CUP
Knowledge Level=Oracle
2025.04
649.1
55.2
-
TraCeS
Knowledge Level=Zero K...
2025.04
590.5
21.4
6,521
TraCeS
Knowledge Level=Zero K...
2025.04
590.5
21.4
6,521
Feedback
Search any
task
Search any
task