Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Reinforcement Learning on SafetyPointGoal1 v0
Loading...
27.45
Reward
DDPG-AdaGamma
23.342
24.4085
25.475
26.5415
May 7, 2026
Reward
Cost
Updated 26d ago
Evaluation Results
Method
Method
Links
Reward
Cost
DDPG-AdaGamma
Base Algorithm=DDPG, D...
2026.05
27.45
46.15
DDPG-Fixed-γ
Base Algorithm=DDPG, D...
2026.05
27.34
51.45
DDPG-CrossValidate
Base Algorithm=DDPG, D...
2026.05
27.26
53.85
DDPG-Uncertainty
Base Algorithm=DDPG, D...
2026.05
27.1
52.7
TRPO-AdaGamma
Base Algorithm=TRPO, D...
2026.05
25.93
49.4
TRPO-Fixed-γ
Base Algorithm=TRPO, D...
2026.05
24.48
45.9
TRPO-CrossValidate
Base Algorithm=TRPO, D...
2026.05
24.38
46.35
TRPO-Uncertainty
Base Algorithm=TRPO, D...
2026.05
23.5
64.55
Feedback
Search any
task
Search any
task