NeurIPS 2016poster15 citations
Improving PAC Exploration Using the Median Of Means
Jason Pazis, Ronald E Parr, Jonathan P How
Abstract
We present the first application of the median of means in a PAC exploration algorithm for MDPs. Using the median of means allows us to significantly reduce the dependence of our bounds on the range of values that the value function can take, while introducing a dependence on the (potentially much smaller) variance of the Bellman operator. Additionally, our algorithm is the first algorithm with PAC bounds that can be applied to MDPs with unbounded rewards.
BibTeX
@inproceedings{NIPS2016_139f0874,
author = {Pazis, Jason and Parr, Ronald E and How, Jonathan P},
booktitle = {Advances in Neural Information Processing Systems},
editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Improving PAC Exploration Using the Median Of Means},
url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/139f0874f2ded2e41b0393c4ac5644f7-Paper.pdf},
volume = {29},
year = {2016}
}