Minimizing expected loss for risk-avoiding reinforcement learning.
Jung-Jung YehTsung-Ting KuoWilliam ChenShou-De LinPublished in: DSAA (2014)
Keyphrases
- expected loss
- reinforcement learning
- active learning
- error rate
- decision rules
- function approximation
- model free
- learning algorithm
- reinforcement learning algorithms
- robotic control
- optimal policy
- transfer learning
- temporal difference
- machine learning
- learning problems
- learning process
- multi agent
- temporal difference learning
- reinforcement learning methods
- rough sets
- markov decision processes
- optimal control
- pattern recognition
- feature selection