Reinforcement Learning, Bit by Bit
release_p4d65etalradraoonq6ex3alla
by
Xiuyuan Lu, Benjamin Van Roy, Vikranth Dwaracherla, Morteza Ibrahimi, Ian Osband, Zheng Wen
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) |
2103.04047v6
access all versions, variants, and formats of this works (eg, pre-prints)