Learning control under uncertainty: A probabilistic Value-Iteration approach.
Bastian BischoffDuy Nguyen-TuongHeiner MarkertAlois C. KnollPublished in: ESANN (2013)
Keyphrases
- learning algorithm
- reinforcement learning
- control rules
- knowledge acquisition
- adaptive control
- uncertain data
- dynamic programming
- robot control
- online learning
- data sets
- prior knowledge
- learning process
- probabilistic model
- learning tasks
- bayesian networks
- knowledge base
- machine learning
- latent variable models
- neural network