Adaptive Training Environment without Prior Knowledge: Modeling Feedback Selection as a Multi-armed Bandit Problem.
Rémy FrenoyYann SoullardIndira ThouveninOlivier GapennePublished in: UMAP (2016)
Keyphrases
- prior knowledge
- virtual training
- echo state networks
- adaptive behavior
- training sessions
- training samples
- bayesian framework
- selection strategy
- data sets
- test set
- generative model
- mobile robot
- training set
- training examples
- virtual world
- training process
- changing environment
- complex environments
- virtual environment
- modeling method
- restricted boltzmann machine
- online learning