Reinforcement Learning, Bit by Bit release_p4d65etalradraoonq6ex3alla

by Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen

Released as a article .

2022  

Abstract

Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a deeper understanding of information acquisition and representation. We develop concepts and establish a regret bound that together offer principled guidance. The bound sheds light on questions of what information to seek, how to seek that information, and it what information to retain. To illustrate concepts, we design simple agents that build on them and present computational results that demonstrate improvements in data efficiency.
In text/plain format

Archived Files and Locations

application/pdf  1.9 MB
file_kmtznkvcwrh5vnvdqcy3pvs4si
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-02-07
Version   v6
Language   en ?
arXiv  2103.04047v6
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 706fb98e-c90e-46cd-a52f-aa0629674ea9
API URL: JSON