Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees.
Guiliang LiuOliver SchulteWang ZhuQingcan LiPublished in: CoRR (2018)
Keyphrases
- linear model
- reinforcement learning
- regression trees
- least squares
- regression model
- linear models
- linear transformation
- decision trees
- linear transformations
- function approximation
- optimal policy
- state space
- model free
- tree structure
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- optimal control
- nonlinear models
- image sequences
- dynamic programming
- multi agent
- face recognition
- linear svm
- machine learning