On-line Energy Optimization of Hybrid Production Systems Using Actor-Critic Reinforcement Learning.
Dorothea SchwungAndreas SchwungSteven X. DingPublished in: IEEE Conf. on Intelligent Systems (2018)
Keyphrases
- production system
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- optimal control
- reinforcement learning algorithms
- multistage
- function approximation
- approximate dynamic programming
- neuro fuzzy
- gradient method
- optimization problems
- expert systems
- optimization algorithm
- model free
- policy iteration
- multiprocessor architecture
- multi agent
- control problems
- state space
- policy gradient methods
- optimal policy
- natural actor critic
- evaluation function
- optimization method
- average reward
- function approximators
- supervised learning
- machine learning
- linear program
- monte carlo