Q- and A-learning Methods for Estimating Optimal Dynamic Treatment Regimes
Phillip J. SchulteAnastasios A. TsiatisEric B. LaberMarie DavidianPublished in: CoRR (2012)
Keyphrases
- learning algorithm
- learning systems
- learning problems
- machine learning
- reinforcement learning
- learning tasks
- human experts
- worst case
- online learning
- machine learning methods
- learning process
- benchmark datasets
- significant improvement
- computational cost
- neural nets
- linear regression
- empirical studies
- optimal control
- inductive inference
- kernel learning
- learned models
- semi supervised learning
- unsupervised learning
- data sets
- mobile robot
- dynamic programming
- active learning
- prior knowledge
- training set
- data mining