Exact Solutions to Time-Dependent MDPs

Abstract

We describe an extension of the Markov decision process model in which a continuous time dimension is included in the state space. This allows for the representation and exact solution of a wide range of problems in which transitions or rewards vary over time. We examine problems based on route planning with public trans(cid:173) portation and telescope observation scheduling.

Cite

Text

Boyan and Littman. "Exact Solutions to Time-Dependent MDPs." Neural Information Processing Systems, 2000.

Markdown

[Boyan and Littman. "Exact Solutions to Time-Dependent MDPs." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/boyan2000neurips-exact/)

BibTeX

@inproceedings{boyan2000neurips-exact,
  title     = {{Exact Solutions to Time-Dependent MDPs}},
  author    = {Boyan, Justin A. and Littman, Michael L.},
  booktitle = {Neural Information Processing Systems},
  year      = {2000},
  pages     = {1026-1032},
  url       = {https://mlanthology.org/neurips/2000/boyan2000neurips-exact/}
}