Deep Reinforcement Learning with Hierarchical Structures

IJCAI 2021 pp. 4899-4900

doi:10.24963/IJCAI.2021/681 /ijcai/2021/li2021ijcai-deep-a/

Abstract

Hierarchical reinforcement learning (HRL), which enables control at multiple time scales, is a promising paradigm to solve challenging and long-horizon tasks. In this paper, we briefly introduce our work in bottom-up and top-down HRL and outline the directions for future work.

PDF IJCAI Semantic Scholar

Cite

Text

Li. "Deep Reinforcement Learning with Hierarchical Structures." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/681

Markdown

[Li. "Deep Reinforcement Learning with Hierarchical Structures." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/li2021ijcai-deep-a/) doi:10.24963/IJCAI.2021/681

BibTeX

@inproceedings{li2021ijcai-deep-a,
  title     = {{Deep Reinforcement Learning with Hierarchical Structures}},
  author    = {Li, Siyuan},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {4899-4900},
  doi       = {10.24963/IJCAI.2021/681},
  url       = {https://mlanthology.org/ijcai/2021/li2021ijcai-deep-a/}
}