ML Anthology

Deictic Option Schemas

Balaraman Ravindran, Andrew G. Barto, Vimal Mathew
IJCAI 2007 pp. 1023-1028
/ijcai/2007/ravindran2007ijcai-deictic/

Abstract

Deictic representation is a representational paradigm, based on selective attention and pointers, that allows an agent to learn and reason about rich complex environments. In this article we present a hierarchical reinforcement learning framework that employs aspects of deictic representation. We also present a Bayesian algorithm for learning the correct representation for a given sub-problem and empirically validate it on a complex game environment.

PDF Semantic Scholar

Cite

Text

Ravindran et al. "Deictic Option Schemas." International Joint Conference on Artificial Intelligence, 2007.

Markdown

[Ravindran et al. "Deictic Option Schemas." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/ravindran2007ijcai-deictic/)

BibTeX

@inproceedings{ravindran2007ijcai-deictic,
  title     = {{Deictic Option Schemas}},
  author    = {Ravindran, Balaraman and Barto, Andrew G. and Mathew, Vimal},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2007},
  pages     = {1023-1028},
  url       = {https://mlanthology.org/ijcai/2007/ravindran2007ijcai-deictic/}
}