Reducing Action Space: Reference-Model-Assisted Deep Reinforcement Learning for Inverter-based Volt-Var Control.
Qiong LiuYe GuoLirong DengHaotian LiuDongyu LiHongbin SunPublished in: CoRR (2022)
Keyphrases
- reference model
- action space
- reinforcement learning
- state space
- control policies
- action selection
- control problems
- markov decision processes
- real valued
- state and action spaces
- reference models
- continuous state
- software architecture
- continuous state spaces
- control policy
- reinforcement learning methods
- metamodel
- control system
- stochastic processes
- optimal control
- markov decision process
- function approximators
- random variables
- machine learning
- open source
- reinforcement learning algorithms
- markov random field
- multi agent
- function approximation
- search algorithm