Online Multi-Task Gradient Temporal-Difference Learning.
Vishnu Purushothaman SreenivasanHaitham Bou-AmmarEric EatonPublished in: AAAI (2014)
Keyphrases
- multi task
- temporal difference learning
- multi task learning
- learning tasks
- function approximation
- reinforcement learning
- fixed point
- multi class
- temporal difference
- game playing
- evaluation function
- feature selection
- transfer learning
- learning problems
- markov decision process
- information gain
- function approximators
- data sets
- bayesian networks