ML Anthology

Learning to Take Concurrent Actions

Khashayar Rohanimanesh, Sridhar Mahadevan
NeurIPS 2002 pp. 1651-1658
/neurips/2002/rohanimanesh2002neurips-learning/

Abstract

We investigate a general semi-Markov Decision Process (SMDP) framework for modeling concurrent decision making, where agents learn optimal plans over concurrent temporally extended actions. We introduce three types of parallel termination schemes { all, any and continue { and theoretically and experimentally compare them.

PDF NeurIPS Semantic Scholar

Cite

Text

Rohanimanesh and Mahadevan. "Learning to Take Concurrent Actions." Neural Information Processing Systems, 2002.

Markdown

[Rohanimanesh and Mahadevan. "Learning to Take Concurrent Actions." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/rohanimanesh2002neurips-learning/)

BibTeX

@inproceedings{rohanimanesh2002neurips-learning,
  title     = {{Learning to Take Concurrent Actions}},
  author    = {Rohanimanesh, Khashayar and Mahadevan, Sridhar},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {1651-1658},
  url       = {https://mlanthology.org/neurips/2002/rohanimanesh2002neurips-learning/}
}