Supplementary materials for paper End-to-End Data-Driven Safe Deep Reinforcement Learning for Distribution Network Scheduling with Hybrid Action Spaces

<p dir="ltr">This is the supplementary materials for the paper End-to-End Data-Driven Safe Deep Reinforcement Learning for Distribution Network Scheduling with Hybrid Action Spaces, containing the topologies of IEEE 33- and 136-bus systems and some key hyper-parameters used in the case study.</p>