From self-driving cars to video games, reinforcement learning (machine learning through interaction with the environment) could have a significant impact. That might feel especially true, for example, if you’re a passenger late for dinner in a self-driving car that has learned an efficient way to get home.
Newton R. Wilson and Sarah Louisa Glasgow Wilson, professors in the Department of Electrical and Systems Engineering in the McKelvey School of Engineering at Washington University in St. Louis, co-authored a paper on reinforcement learning with a particular focus on infinite-dimensional systems with postdoctoral researcher Wei Zhang. This paper was published in the Journal of Machine Learning Research.
If the system is very large, the movement of hundreds of thousands of elements must be accounted for, which seems to take forever, Lee said. The proposed reinforcement learning involves the derivation of new formulations and effective algorithms to find optimal results for arbitrary large-scale systems.
“Our research has the potential to touch so many fields, including medicine,” Lee said. “And a lot of the technologies are just getting more and more complex. We hope to be part of the solution.”
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are those of the authors alone. Read the full text here.
