Bridging Transient and Steady-State Performance in Voltage Control: A Reinforcement Learning Approach with Safe Gradient Flow.
Jie FengWenqi CuiJorge CortésYuanyuan ShiPublished in: CoRR (2023)
Keyphrases
- steady state
- operating conditions
- reinforcement learning
- markov chain
- gradient flow
- control problems
- optimal control
- explicit expressions
- field effect transistors
- curve evolution
- product form
- energy functional
- state dependent
- robot control
- arrival rate
- machine learning
- control system
- service times
- active contour model
- queueing networks
- queue length
- control strategy
- dynamic programming
- scale space
- high density
- queueing model
- active contours
- optimal policy