Scalar Posterior Sampling with Applications
Georgios Theocharous, Zheng Wen, Yasin Abbasi Yadkori, Nikos Vlassis
Abstract
We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity. We prove a Bayesian regret bound under mild assumptions. Our result is more generally applicable to multiple parameters and continuous state action problems. We compare our algorithm with state-of-the-art PSRL algorithms on standard discrete and continuous problems from the literature. Finally, we show how the assumptions of our algorithm satisfy a sensible parameterization for a large class of problems in sequential recommendations.
BibTeX
@inproceedings{NEURIPS2018_c157297d,
author = {Theocharous, Georgios and Wen, Zheng and Abbasi Yadkori, Yasin and Vlassis, Nikos},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Scalar Posterior Sampling with Applications},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/c157297d1a1ff043255bfb18530caaa2-Paper.pdf},
volume = {31},
year = {2018}
}