Discovering Hierarchy in Reinforcement Learning with HEXQ

Abstract

An open problem in reinforcement learning is discovering hierarchical structure. HEXQ, an algorithm which automatically attempts to decompose and solve a model-free factored MDP hierarchically is described. By searching for aliased Markov sub-space regions based on the state variables the algorithm uses temporal and state abstraction to construct a hierarchy of interlinked smaller MDPs. 1.

Cite

Text

Hengst. "Discovering Hierarchy in Reinforcement Learning with HEXQ." International Conference on Machine Learning, 2002.

Markdown

[Hengst. "Discovering Hierarchy in Reinforcement Learning with HEXQ." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/hengst2002icml-discovering/)

BibTeX

@inproceedings{hengst2002icml-discovering,
  title     = {{Discovering Hierarchy in Reinforcement Learning with HEXQ}},
  author    = {Hengst, Bernhard},
  booktitle = {International Conference on Machine Learning},
  year      = {2002},
  pages     = {243-250},
  url       = {https://mlanthology.org/icml/2002/hengst2002icml-discovering/}
}