Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices.
Haotian LiuWenchuan WuPublished in: CoRR (2021)
Keyphrases
- bi level
- reinforcement learning
- control problems
- continuous state spaces
- continuous domains
- gray scale
- continuous state and action spaces
- discrete space
- control system
- optimal control
- continuous action
- robot control
- action space
- pricing model
- continuous variables
- mobile devices
- continuous space
- continuous data
- discrete variables
- continuous state
- function approximation
- robotic control
- state space
- dynamic programming
- remote control
- action selection
- control strategy
- learning process
- color images
- temporal difference
- control strategies
- model free
- multi agent
- continuous valued
- mobile applications
- hands free
- markov decision processes
- learning algorithm