From autonomous cars to video games, reinforcement learning (machine learning through interaction with environments) can have an important impact. That may feel especially true, for example, when you’re a passenger late for dinner in an autonomous car that has learned the efficient way home.
Jr-Shin Li, the Newton R. and Sarah Louisa Glasgow Wilson Professor of electrical and systems engineering at the McKelvey School of Engineering at Washington University in St. Louis, co-authored a paper with postdoctoral research associate Wei Zhang on reinforcement learning with a particular focus on infinite-dimensional systems. The paper was published in the Journal of Machine Learning Research.
If a system is extremely large, then you must account for the movements of hundreds of thousands of factors, which can seemingly take forever, Li said. The proposed reinforcement learning involves a new formulation and the derivation of effective algorithms to find optimal outcomes for arbitrarily large systems.
“Our work can touch on so many areas, including medicine,” Li said. “And so much technology is only getting more complex. We hope to be a part of the solution.”
Read more on the McKelvey Engineering website.
