Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safe Reinforcement Learning on double-gates+ Differential Drive dynamics
Loading...
0.2
Mean Safety Violations per Episode
TD3
-0.276
2.937
6.15
9.363
May 22, 2024
Mean Safety Violations per Episode
Mean Shield Invocations per Episode
SD Shield Invocations per Episode
SD Safety Violations per Episode
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Safety Violations per Episode
Mean Shield Invocations per Episode
SD Shield Invocations per Episode
SD Safety Violations per Episode
TD3
2024.05
0.2
-
-
0.4
PPO-lag
2024.05
6.9
-
-
6.1
CPO
2024.05
12.1
-
-
2.9
DMPS
2024.05
-
18.4
13
-
MPS
2024.05
-
106.2
18.5
-
Feedback
Search any
task
Search any
task
