Multi-armed Bandits for Task Assignment

Multi-armed bandits have been used in multiple contexts that call for a mixture of exploration and exploitation strategies. We are considering this paradigm in the context of repeated assignment of tasks to teams. We assume a latent structured space that encodes the attributes of individuals, teams, and tasks. The goal of the project is to use the structure of the space to develop efficient algorithms for the assignment of single and multiple tasks to teams.

Affiliated People

Research interests: 

Applied Machine Learning, Complex Network Analysis, Convex Optimization, Multi-Agent Systems, Natural Language Processing

Omid received a B.Sc in Computer Engineering in 2011 and M.Sc. in Artificial Intelligence in 2014 from Sharif University of Technology, Tehran, Iran. Prior to joining Dynamo lab in 2015, he spent few years as a software engineer in industry. He has a background in complex networks, analysis of financial data and applied machine learning.

Research interests: 

computational methods for group dynamics in teams and organizations, decision theory for groups and inviduals, and methods of online learning & optimization.

Alex received his B.Sc. Computer Science & Engineering with a Minor in Mathematics from University of Southern Calfornia in 2015.