Trustable Deep Reinforcement Learning with Efficient Data Utilization

Speaker: Zahra Mahmoodzadeh
Affiliation: Ph.D. Candidate

Abstract:  We live in the era of big data in which the advancement of sensor and monitoring technologies, data storage and management, and computer processing power enable us to acquire, store and process over 2.5 Quintilian bytes of data daily. This massive data brings the necessity of using trustable and high-performance data-driven models that extract knowledge out of data. This dissertation focuses on learning to solve highly risk-averse and complex sequential decision-making problems from retrospective data sets by deep Reinforcement Learning (RL).

Deep RL has gained remarkable breakthroughs in many applications. It achieved superhuman performance in video and Atari games, defeated the world champion in game of Go, gained competent autonomy in simulated self-driving cars, and successfully learned to perform some robotic tasks. Despite all the notable advancements in deep RL, its application to real-world problems such as clinical treatment policy or industrial asset maintenance management is insignificant. Studies are underway to investigate deep RL use in realistic problems; however, none has been deployed in real-world settings. Several limitations hinder the deep RL application to real-world problems, among which trustability and excessive thirst for data are the main issues. This research is an effort to smooth the way of applying deep RL to real-world problems by addressing the above two limitations.

Biography: Zahra Mahmoodzadeh received her BSc and MSc degrees from the Electrical Engineering department of Sharif University in 2011 and 2013 respectively. She joined Professor Mosleh’s research group at Garrick Institute of Risk Sciences in September of 2016 as an ECE Ph.D. student. Her research involves the reliability and trustability of artificial intelligence decision-making techniques in highly risk-averse domains.

For more information, contact Prof. Ali Mosleh (mosleh@ucla.edu)

Date/Time:
Date(s) - Dec 11, 2020
2:00 pm - 3:30 pm

Location:
Via Zoom Only
No location, Los Angeles
Map Unavailable