ML Anthology

Relational Temporal Difference Learning

Nima Asgharbeygi, David J. Stracuzzi, Pat Langley
ICML 2006 pp. 49-56
doi:10.1145/1143844.1143851 /icml/2006/asgharbeygi2006icml-relational/

Abstract

We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal difference reinforcement to learn a distributed value function represented over a conceptual hierarchy of relational predicates. We present experiments using two domains from the General Game Playing repository, in which we observe that our system achieves higher learning rates than non-relational methods. We also discuss related work and directions for future research.

PDF ICML Semantic Scholar

Cite

Text

Asgharbeygi et al. "Relational Temporal Difference Learning." International Conference on Machine Learning, 2006. doi:10.1145/1143844.1143851

Markdown

[Asgharbeygi et al. "Relational Temporal Difference Learning." International Conference on Machine Learning, 2006.](https://mlanthology.org/icml/2006/asgharbeygi2006icml-relational/) doi:10.1145/1143844.1143851

BibTeX

@inproceedings{asgharbeygi2006icml-relational,
  title     = {{Relational Temporal Difference Learning}},
  author    = {Asgharbeygi, Nima and Stracuzzi, David J. and Langley, Pat},
  booktitle = {International Conference on Machine Learning},
  year      = {2006},
  pages     = {49-56},
  doi       = {10.1145/1143844.1143851},
  url       = {https://mlanthology.org/icml/2006/asgharbeygi2006icml-relational/}
}