Deep Reinforcement Learning Based Grid-Forming Inverter.
Ebrahim BaloujiKarl BäckströmTomas McKelveyPublished in: IAS (2023)
Keyphrases
- reinforcement learning
- function approximation
- grid computing
- state space
- markov decision processes
- grid points
- temporal difference
- control algorithm
- model free
- dynamic programming
- learning algorithm
- multi agent
- learning process
- action selection
- reinforcement learning algorithms
- induction motor
- stochastic approximation
- grid environment
- pulse width modulation
- robotic control
- grid structure
- machine learning
- transition model
- temporal difference learning
- input output
- optimal policy
- distributed computing
- monte carlo