Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
Liyu Chen, Rahul Jain, Haipeng Luo
Abstract
We introduce two new no-regret algorithms for the stochastic shortest path (SSP) problem with a linear MDP that significantly improve over the only existing results of (Vial et al., 2021). Our first algorithm is computationally efficient and achieves a regret bound $O(\sqrt{d^3B_{\star}^2T_{\star} K})$, where $d$ is the dimension of the feature space, $B_{\star}$ and $T_{\star}$ are upper bounds of the expected costs and hitting time of the optimal policy respectively, and $K$ is the number of episodes. The same algorithm with a slight modification also achieves logarithmic regret of order $O(\frac{d^3B_{\star}^4}{c_{\min}^2\text{\rm gap}_{\min} }\ln^5\frac{dB_{\star} K}{c_{\min}})$, where $\text{\rm gap}_{\min}$ is the minimum sub-optimality gap and $c_{\min}$ is the minimum cost over all state-action pairs. Our result is obtained by developing a simpler and improved analysis for the finite-horizon approximation of (Cohen et al., 2021) with a smaller approximation error, which might be of independent interest. On the other hand, using variance-aware confidence sets in a global optimization problem, our second algorithm is computationally inefficient but achieves the first “horizon-free” regret bound $O(d^{3.5}B_{\star}\sqrt{K})$ with no polynomial dependency on $T_{\star}$ or $1/c_{\min}$, almost matching the $\Omega(dB_{\star}\sqrt{K})$ lower bound from (Min et al., 2021).
BibTeX
@InProceedings{pmlr-v162-chen22h,
title = {Improved No-Regret Algorithms for Stochastic Shortest Path with Linear {MDP}},
author = {Chen, Liyu and Jain, Rahul and Luo, Haipeng},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {3204--3245},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/chen22h/chen22h.pdf},
url = {https://proceedings.mlr.press/v162/chen22h.html},
abstract = {We introduce two new no-regret algorithms for the stochastic shortest path (SSP) problem with a linear MDP that significantly improve over the only existing results of (Vial et al., 2021). Our first algorithm is computationally efficient and achieves a regret bound $O(\sqrt{d^3B_{\star}^2T_{\star} K})$, where $d$ is the dimension of the feature space, $B_{\star}$ and $T_{\star}$ are upper bounds of the expected costs and hitting time of the optimal policy respectively, and $K$ is the number of episodes. The same algorithm with a slight modification also achieves logarithmic regret of order $O(\frac{d^3B_{\star}^4}{c_{\min}^2\text{\rm gap}_{\min} }\ln^5\frac{dB_{\star} K}{c_{\min}})$, where $\text{\rm gap}_{\min}$ is the minimum sub-optimality gap and $c_{\min}$ is the minimum cost over all state-action pairs. Our result is obtained by developing a simpler and improved analysis for the finite-horizon approximation of (Cohen et al., 2021) with a smaller approximation error, which might be of independent interest. On the other hand, using variance-aware confidence sets in a global optimization problem, our second algorithm is computationally inefficient but achieves the first “horizon-free” regret bound $O(d^{3.5}B_{\star}\sqrt{K})$ with no polynomial dependency on $T_{\star}$ or $1/c_{\min}$, almost matching the $\Omega(dB_{\star}\sqrt{K})$ lower bound from (Min et al., 2021).}
}