Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees.
Guiliang LiuOliver SchulteWang ZhuQingcan LiPublished in: ECML/PKDD (2) (2018)
Keyphrases
- linear model
- reinforcement learning
- regression trees
- least squares
- regression model
- linear models
- function approximation
- linear transformation
- decision trees
- model free
- nonlinear models
- reinforcement learning algorithms
- additive model
- state space
- learning algorithm
- markov decision processes
- temporal difference
- multi agent
- machine learning
- tree structure
- markov chain
- linear transformations