- This event has passed.
STEM Bytes Seminar
March 5 @ 10:00 am - 10:30 am
Next month’s STEM Bytes Seminar will be on Tuesday, March 5 from 10:00 – 10:30 am PT on Zoom!
To register for this seminar, please visit: tinyurl.com/STEM-Bytes3-5 (link in bio)
Speaker:
๐คThejani Gamage, PhD Student in Mathematics
PhD candidate in the Mathematics Department in Univ. Of Southern California. Research Focus is Financial Mathematics, in particular the optimization problems in Insurance Companies using concepts from Reinforcement Learning. Recipient of the Dornsife Gold Fellowship for Summer 2023. I like reading fictions and cooking dishes from around the world for fun.
Talk: Reinforcement Learning for Stochastic Control
Reinforcement Learning (RL) is one of the 3 pillars of machine learning, along with supervised and unsupervised Learning. RL can theoretically learn how to perform any task by learning via trial and error, essentially how any animal in the animal kingdom learns how to perform a task. Examples of use of RL include playing games (ex. AlphaGo), Robotics and automation, scheduling and optimization, trading, recommender systems etc. Though theoretically sounds limitless, RL is not without its limitations, which mainly include sample in-efficicincy, exploration and exploitation trade off and the sparse-reward problem. These problems and many useful applications of RL have made it one of the most active research topics both in academia and industry.
๐๐ค๐ฉ๐: ๐๐๐๐จ ๐๐ซ๐๐ฃ๐ฉ ๐๐จ ๐ค๐ฅ๐๐ฃ ๐ฉ๐ค ๐ฉ๐๐ ๐๐๐พ ๐๐ค๐ข๐ข๐ช๐ฃ๐๐ฉ๐ฎ