Presenter
Xiuyuan (Lucy) Lu
Research Scientist,
DeepMind, Mountain View
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 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.
Reference
https://arxiv.org/pdf/2103.04047.pdf
Bio
Xiuyuan Lu is a research scientist at DeepMind. She is interested in building data-efficient reinforcement learning agents. She obtained her PhD in 2020 from the Department of Management Science and Engineering at Stanford University.