Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Machine Learning
2022-05-30 v3 Machine Learning
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 certain computation oracle.
Cite
@article{arxiv.2105.01593,
title = {Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation},
author = {Daniel Vial and Advait Parulekar and Sanjay Shakkottai and R. Srikant},
journal= {arXiv preprint arXiv:2105.01593},
year = {2022}
}
Comments
This version removes most assumptions of the prior one