Improving PAC exploration using the median of means
Name
6577-improving-pac-exploration-using-the-median-of-means.pdf
Size
470.04 KB
Format
Adobe PDF
Checksum (MD5)
80f1ed99788bd59e4ac28a9d4de0672e
Author(s)
Pazis, Jason
How, Jonathan P
Date Issued
2016
Journal
Advances in Neural Information Processing Systems (NIPS)
Publisher
Neural Information Processing Systems Foundation
Citation
Pazis, Jason et al. "Improving PAC Exploration Using the Median Of Means." Advances in Neural Information Processing Systems (NIPS 2016), 29 (2016) © 2016 NIPS Foundation - All Rights Reserved.
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Aerospace Controls Laboratory
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/6577-improving-pac-exploration-using-the-median-of-means
