Using Predictive Representations to Improve Generalization in Reinforcement Learning

Rafols, Eddie J.; Ring, Mark B.; Sutton, Richard S.; Tanner, Brian

Using Predictive Representations to Improve Generalization in Reinforcement Learning

Eddie J. Rafols, Mark B. Ring, Richard S. Sutton, Brian Tanner

Download BibTeX Cite

Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 835-839.

Abstract

The predictive representations hypothesis holds that particularly good generalization will result from representing the state of the world in terms of predictions about possible future experience. This hypothesis has been a central motivation behind recent research in, for example, PSRs and TD networks. In this paper we present the first explicit investigation of this hypothesis. We show in a reinforcement-learning example (a grid-world navigation task) that a predictive representation in tabular form can learn much faster than both the tabular explicit-state representation and a tabular history-based method.

Eddie J. Rafols, Mark B. Ring, Richard S. Sutton, and Brian Tanner. 2005. Using Predictive Representations to Improve Generalization in Reinforcement Learning. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 835–839. https://ijcai.org/proceedings/2005/227

@inproceedings{ijcai2005p227,
  title     = {Using Predictive Representations to Improve Generalization in Reinforcement Learning},
  author    = {Rafols, Eddie J. and Ring, Mark B. and Sutton, Richard S. and Tanner, Brian},
  booktitle = {Proceedings of the Nineteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-05}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  pages     = {835--839},
  year      = {2005},
  url       = {https://ijcai.org/proceedings/2005/227},
}

TY  - CPAPER
TI  - Using Predictive Representations to Improve Generalization in Reinforcement Learning
AU  - Rafols, Eddie J.
AU  - Ring, Mark B.
AU  - Sutton, Richard S.
AU  - Tanner, Brian
T2  - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2005
SP  - 835
EP  - 839
UR  - https://ijcai.org/proceedings/2005/227
ER  -