ML Anthology

Learning the Persistence of Actions in Reactive Control Rules

Helen G. Cobb, John J. Grefenstette
ICML 1991 pp. 292-297
doi:10.1016/B978-1-55860-200-7.50061-1 /icml/1991/cobb1991icml-learning/

Abstract

This paper explores the effect of explicitly searching for the persistence of each decision in a time-dependent sequential decision task. In prior studies, Grefenstette, et al, show the effectiveness of SAMUEL, a genetic algorithm-based system, in solving a simulation problem where an agent learns how to evade a predator that is in pursuit. In their work, an agent applies a control action at each time step. This paper examines a reformulation of the problem: the agent learns not only the level of response of a control action, but also how long to apply that control action. By examining this problem, the work shows that it is appropriate to choose a representation of the state space that compresses time information when solving a time-dependent sequential decision problem. By compressing time information, critical events in the decision sequence become apparent.

ICML Semantic Scholar

Cite

Text

Cobb and Grefenstette. "Learning the Persistence of Actions in Reactive Control Rules." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50061-1

Markdown

[Cobb and Grefenstette. "Learning the Persistence of Actions in Reactive Control Rules." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/cobb1991icml-learning/) doi:10.1016/B978-1-55860-200-7.50061-1

BibTeX

@inproceedings{cobb1991icml-learning,
  title     = {{Learning the Persistence of Actions in Reactive Control Rules}},
  author    = {Cobb, Helen G. and Grefenstette, John J.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {292-297},
  doi       = {10.1016/B978-1-55860-200-7.50061-1},
  url       = {https://mlanthology.org/icml/1991/cobb1991icml-learning/}
}