@inproceedings{0f2ba51850814f9a99e35c9a0e7a4065,
title = "Learning Good State and Action Representations via Tensor Decomposition",
abstract = "The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding.",
author = "Chengzhuo Ni and Zhang, {Anru R.} and Yaqi Duan and Mengdi Wang",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Symposium on Information Theory, ISIT 2021 ; Conference date: 12-07-2021 Through 20-07-2021",
year = "2021",
month = jul,
day = "12",
doi = "10.1109/ISIT45174.2021.9518158",
language = "English (US)",
series = "IEEE International Symposium on Information Theory - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1682--1687",
booktitle = "2021 IEEE International Symposium on Information Theory, ISIT 2021 - Proceedings",
address = "United States",
}