arXiv Open Access 2023

When do discounted-optimal policies also optimize the gain?

Victor Boone
Lihat Sumber

Abstrak

In this technical note, we establish an upper-bound on the threshold on the discount factor starting from which all discounted-optimal deterministic policies are gain-optimal, that we prove to be tight on an example. To address computability issues of that theoretical threshold, we provide a weaker bound which is tractable on ergodic MDPs in polynomial time.

Topik & Kata Kunci

Penulis (1)

V

Victor Boone

Format Sitasi

Boone, V. (2023). When do discounted-optimal policies also optimize the gain?. https://arxiv.org/abs/2304.08048

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓