• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • News
  • Seminars
    • CESG Seminars
    • Fishbowl Seminar Series
    • Computer Engineering Eminent Scholar Seminar Series
    • Topics In Systems Seminar
    • Related Seminars
  • People
    • Faculty
    • Staff
    • Current Visitors
    • Students
  • Research
  • Academics
    • Graduate
    • Undergraduate
  • All Courses
  • Contact
  • Information
    • Information
    • Technology Resources
    • Directions

Computer Engineering and Systems Group

Texas A&M University College of Engineering

CESG Seminar – Mohammad Ghavamzadeh

Posted on October 28, 2022 by Vickie Winston

Friday, November 11, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr.  Mohammad Ghavamzadeh
Senior Staff Research Scientist
Google

Title: “Mitigating the Risk Associated with Epistemic and Aleatory Uncertainties in MDPs”

Abstract
Prior work on safe reinforcement learning (RL) has studied risk-aversion to randomness in dynamics (aleatory) and to model uncertainty (epistemic) in isolation. We propose and analyze a new framework to jointly model the risk associated with epistemic and aleatory uncertainties in finite-horizon and discounted infinite-horizon MDPs. We call this framework that combines risk-averse and soft-robust methods RASR. We show that when the risk-aversion is defined using either the entropic value-at-risk (EVaR) or the entropic risk measure (ERM), the optimal policy in RASR can be computed efficiently using a new dynamic program formulation with a time-dependent risk level. As a result, the optimal risk-averse policies are deterministic but time-dependent, even in the infinite-horizon discounted setting. We also show that particular RASR objectives reduce to risk-averse RL with mean posterior transition probabilities. Our empirical results show that our new algorithms consistently mitigate uncertainty as measured by EVaR and other standard risk measures.

Biography 
Dr. Mohammad Ghavamzadeh received a Ph.D. degree from UMass Amherst in 2005. He was a postdoctoral fellow at UAlberta from 2005 to 2008. He was a permanent researcher at INRIA from 2008 to 2013. He was the recipient of the “INRIA award for scientific excellence” in 2011, and obtained his Habilitation in 2014. Since 2013, he has been a senior researcher at Adobe and FAIR, and now a senior staff research scientist at Google. He has published over 100 refereed papers in major machine learning, AI, and control journals and conferences. He has co-chaired more than 10 workshops and tutorials at NeurIPS, ICML, and AAAI. His research has been mainly focused on the areas of reinforcement learning, bandit algorithms, and recommendation systems.

More information on Dr. Ghavamzadeh can be found at
https://mohammadghavamzadeh.github.io/
https://scholar.google.ca/citations?user=Bo-wyrkAAAAJ&hl=en

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

* Friday, 11/11/22 at 10:20 a.m. via Zoom *

Filed Under: Uncategorized

Recent NEWS

  • CESG Seminar: Peipei Zhou March 1, 2023
  • CESG Seminar – Desik Rengarajan February 21, 2023
  • CESG Seminar – Manoranjan Majji February 13, 2023
  • CESG Seminar – Jiang Hu February 2, 2023
  • CESG Seminar – Sabit Ekin January 24, 2023
  • Congratulations Dr. Hu! January 13, 2023
  • Congratulations Fall 2022 Graduates! December 12, 2022

© 2016–2023 Computer Engineering and Systems Group Log in

Texas A&M Engineering Experiment Station Logo
  • State of Texas
  • Open Records
  • Risk, Fraud & Misconduct Hotline
  • Statewide Search
  • Site Links & Policies
  • Accommodations
  • Environmental Health, Safety & Security
  • Employment