English

Unbounded Dynamic Programming via the Q-Transform

Optimization and Control 2022-08-02 v2 Theoretical Economics

Abstract

We propose a new approach to solving dynamic decision problems with unbounded rewards based on the transformations used in Q-learning. In our case, the objective of the transform is to convert an unbounded dynamic program into a bounded one. The approach is general enough to handle problems for which existing methods struggle, and yet simple relative to other techniques and accessible for applied work. We show by example that many common decision problems satisfy our conditions.

Keywords

Cite

@article{arxiv.2012.00219,
  title  = {Unbounded Dynamic Programming via the Q-Transform},
  author = {Qingyin Ma and John Stachurski and Alexis Akira Toda},
  journal= {arXiv preprint arXiv:2012.00219},
  year   = {2022}
}

Comments

arXiv admin note: text overlap with arXiv:1911.13025