Reinforcement Learning for Production Ramp-Up: A Q-Batch Learning Approach.
Stefanos DoltsinisPedro FerreiraNiels LohsePublished in: ICMLA (1) (2012)
Keyphrases
- principal component analysis
- batch learning
- reinforcement learning
- incremental learning
- confidence weighted
- feature extraction
- function approximation
- concept drift
- reinforcement learning algorithms
- machine learning
- temporal difference
- markov decision processes
- optimal policy
- multi agent
- learning process
- optimal control
- state space
- learning algorithm
- dynamic programming
- function approximators
- neural network
- model free
- similarity measure
- clustering algorithm
- data sets
- production planning
- production system
- support vector
- multimedia