Reinforcement Learning in the Real-world: How to “cheat” and still feel good about it

Abstract

Reinforcement learning has had many successes, but significant amounts of time and/or data can be required to reach acceptable performance. If agents or robots are to be deployed in real-world environments, it is critical that our algorithms take advantage of existing data and human knowledge. This talk will discuss a selection of recent work that improves reinforcement learning by leveraging demonstrations and feedback from imperfect users, with an emphasis on how interactive machine learning can be extended to best leverage the unique abilities of both computers and humans.

Notes

• Dr Matthew E. Taylor is an Associate Professor of Computing Science at the University of Alberta and a Fellow and Fellow-in-Residence at the Alberta Machine Intelligence Institute (Amii). He is the Director of the Intelligent Robot Learning (IRL) Lab (irll.ca)and a Principal Investigator at the Reinforcement Learning & Artificial Intelligence (RLAI) Lab, both at the University of Alberta.

• His publication record on Google Scholar can be found here, and personal website here