Not Logged In

Multi-Time Models for Reinforcement Learning

Reinforcement learning can be used not only to predict rewards, but also to predict states, i.e. to learn a model of the world's dynamics. Models can be defined at different levels of temporal abstraction. Multi-time models are models that focus on predicting what will happen, rather than when a certain event will take place. Based on multi-time models, we can define abstract actions, which enable planning (presumably in a more efficient way) at various levels of abstraction.

Citation

D. Precup, R. Sutton. "Multi-Time Models for Reinforcement Learning". International Conference on Machine Learning (ICML), Nashville, July 1997.

Keywords: abstraction, define, machine learning
Category: In Conference

BibTeX

@incollection{Precup+Sutton:ICML97,
  author = {Doina Precup and Richard S. Sutton},
  title = {Multi-Time Models for Reinforcement Learning},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = 1997,
}

Last Updated: May 24, 2007
Submitted by Christian Smith

University of Alberta Logo AICML Logo