Reduced state space and cost function in reinforcement learning for demand response control of multiple EV charging stations.
Manu LahariyaNasrin SadeghianpourhamamiChris DevelderPublished in: BuildSys@SenSys (2019)
Keyphrases
- state space
- reinforcement learning
- cost function
- electric vehicles
- control problems
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- control strategies
- markov chain
- robot control
- dynamic programming
- function approximation
- intelligent control
- control policy
- learning algorithm
- adaptive control
- optimal control
- heuristic search
- control system
- machine learning
- control policies
- control method
- action space
- continuous state spaces
- control strategy
- global minimum
- sufficient conditions
- resource utilization
- learning process
- multi agent
- macro actions
- reward shaping