Automatically Mapped Transfer between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines.
Haitham Bou-AmmarDecebal Constantin MocanuMatthew E. TaylorKurt DriessensKarl TuylsGerhard WeissPublished in: ECML/PKDD (2) (2013)
Keyphrases
- learning tasks
- transfer learning
- restricted boltzmann machine
- reinforcement learning
- learning algorithm
- multi task
- machine learning algorithms
- supervised learning
- machine learning
- learning experience
- collaborative filtering
- labeled data
- active learning
- deep learning
- semi supervised learning
- neural nets
- text categorization
- information retrieval
- neural network
- semi supervised
- computer vision
- kernel methods
- image processing
- training set
- unlabeled data
- text mining