Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
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.
Cite
Text
Vial et al. "Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation." International Conference on Machine Learning, 2022.Markdown
[Vial et al. "Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation." International Conference on Machine Learning, 2022.](https://mlanthology.org/icml/2022/vial2022icml-regret/)BibTeX
@inproceedings{vial2022icml-regret,
title = {{Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation}},
author = {Vial, Daniel and Parulekar, Advait and Shakkottai, Sanjay and Srikant, R},
booktitle = {International Conference on Machine Learning},
year = {2022},
pages = {22203-22233},
volume = {162},
url = {https://mlanthology.org/icml/2022/vial2022icml-regret/}
}