Discovering Options from Example Trajectories

Abstract

We present a novel technique for automated problem decomposition to address the problem of scalability in Reinforcement Learning. Our technique makes use of a set of near-optimal trajectories to discover {\it options} and incorporates them into the learning process, dramatically reducing the time it takes to solve the underlying problem. We run a series of experiments in two different domains and show that our method offers up to 30 fold speedup over the baseline.

Cite

Text

Zang et al. "Discovering Options from Example Trajectories." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553529

Markdown

[Zang et al. "Discovering Options from Example Trajectories." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/zang2009icml-discovering/) doi:10.1145/1553374.1553529

BibTeX

@inproceedings{zang2009icml-discovering,
  title     = {{Discovering Options from Example Trajectories}},
  author    = {Zang, Peng and Zhou, Peng and Minnen, David and Jr., Charles Lee Isbell},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {1217-1224},
  doi       = {10.1145/1553374.1553529},
  url       = {https://mlanthology.org/icml/2009/zang2009icml-discovering/}
}