Safe Reinforcement Learning for Grid Voltage Control.
Thanh Long VuSayak MukherjeeRenke HuangQiuhua HuangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- robot control
- control system
- temporal difference
- state space
- function approximation
- action selection
- power losses
- real time
- robotic control
- control policies
- control policy
- control strategies
- grid computing
- control strategy
- power system
- mobile robot
- learning process