Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Daniel Vial, Advait Parulekar, Sanjay Shakkottai, R. Srikant

Research output: Contribution to journalConference articlepeer-review

Abstract

We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally efficient, and uses stationary policies. To our knowledge, this is the first such algorithm in the LFA literature (for SSP or other formulations). Our algorithm is a special case of a more general one, which achieves regret square root in the number of episodes given access to a computation oracle.

Original languageEnglish (US)
Pages (from-to)22203-22233
Number of pages31
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Externally publishedYes
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: Jul 17 2022Jul 23 2022

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation'. Together they form a unique fingerprint.

Cite this