List your company

Safe Reinforcement Learning on Spring Pendulum

81.4Training Time (s)CUP
-69.732950.4091,970.552,990.691Oct 14, 2023

Evaluation results

MethodLinks
CUP2023.1081.4
CPO2023.1098.6
DDPG-L2023.10174.9
RPO-DDPG2023.10242.6
SAC-L2023.10309.5
RPO-SAC2023.10419
Safety Layer2023.103,859.7