The Method of Learning Personal Preference with Reinforcement Learning.
Yong Hee ParkWon Seok ChoiSeong Gon ChoiPublished in: ICACT (2022)
Keyphrases
- reinforcement learning
- significant improvement
- high accuracy
- learning process
- learning algorithm
- policy search
- similarity measure
- learning scheme
- clustering method
- computational cost
- function approximators
- learning capabilities
- function approximation
- learning problems
- unsupervised learning
- neural network
- dynamic programming
- computational complexity
- objective function
- support vector machine
- model selection
- active learning
- prior knowledge
- preprocessing
- learning mechanism
- machine learning