Actor-Critic Reinforcement Learning for Energy Optimization in Hybrid production Environments.
Dorothea SchwungAndreas SchwungSteven X. DingPublished in: Int. J. Comput. (2019)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- optimal control
- approximate dynamic programming
- function approximation
- reinforcement learning algorithms
- neuro fuzzy
- gradient method
- state space
- rl algorithms
- optimization algorithm
- markov decision processes
- supervised learning
- dynamic programming
- optimization problems
- multi agent
- control problems
- policy iteration
- average reward
- policy gradient methods
- infinite horizon
- model free
- neural network
- machine learning