Constructing Stochastic Mixture Policies for Episodic Multiobjective Reinforcement Learning Tasks.
Peter VamplewRichard DazeleyEwan BarkerAndrei V. KelarevPublished in: Australasian Conference on Artificial Intelligence (2009)
Keyphrases
- learning tasks
- multi objective
- learning problems
- learning algorithm
- evolutionary algorithm
- reinforcement learning
- transfer learning
- machine learning
- supervised learning
- multi task
- machine learning algorithms
- learning experience
- objective function
- optimal policy
- function approximation
- hypothesis space
- multi task learning
- multi label
- metric learning
- genetic algorithm
- information retrieval
- multitask learning
- kernel methods
- real world
- neural network