Transfer Learning via Inter-Task Mappings for Temporal Difference Learning.
Matthew E. TaylorPeter StoneYaxin LiuPublished in: J. Mach. Learn. Res. (2007)
Keyphrases
- transfer learning
- temporal difference learning
- reinforcement learning
- function approximation
- learning tasks
- fixed point
- knowledge transfer
- evaluation function
- game playing
- cross domain
- temporal difference
- reinforcement learning algorithms
- labeled data
- markov decision process
- machine learning
- collaborative filtering
- learning algorithm
- state space
- model free
- text classification
- active learning
- transfer knowledge
- machine learning algorithms
- text categorization
- markov decision processes
- semi supervised learning
- policy iteration
- training data
- action space
- action selection
- monte carlo
- target domain
- data sets
- text mining
- probabilistic model
- learning process
- pairwise
- data mining
- neural network