People

Mohammad Ghavamzadeh

Research Scientist

I received a Ph.D. degree in Computer Science from the University of Massachusetts Amherst in 2005. From 2005 to 2008, I was a postdoctoral fellow at the University of Alberta. I have been a permanent researcher at INRIA in France since November 2008. I was promoted to first-class researcher in 2010, was the recipient of the “INRIA award for scientific excellence” in 2011, and obtained my Habilitation in 2014. Since 2013, I have been a senior researcher, first at Adobe Research (2013 to May 2017), then at DeepMind (June 2017 to October 2018), and now at Facebook AI Research (FAIR). I have been an area chair and a senior program committee member at NIPS, ICML, IJCAI, and AAAI. I have been on the editorial board of Machine Learning Journal (MLJ) and have been a reviewer for JMLR, MLJ, JAIR, Journal of operations research, IEEE TAC, and Automatica. I have published over 70 refereed papers in major machine learning, AI, and control journals and conferences, and has organized several tutorials and workshops at NIPS, ICML, and AAAI. I have received the best paper award at UAI-2015 and AAMAS-2001. My research is in the areas of machine learning, artificial intelligence, control, and learning theory; particularly to investigate the principles of scalable decision-making and to devise, analyze, and implement algorithms for sequential decision-making under uncertainty and reinforcement learning.

Interests

Reinforcement learning, online learning, bandit algorithms, recommendation systems, learning theory

Related Links

Website

Latest Publications

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies

Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor

NeurIPS - November 27, 2019

Perturbed-History Exploration in Stochastic Multi-Armed Bandits

Branislav Kveton, Csaba Szepesvári, Mohammad Ghavamzadeh, Craig Boutilier

IJCAI - June 30, 2019

Risk-Sensitive Generative Adversarial Imitation Learning

Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow, Marco Pavone

AISTATS - June 20, 2019

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

Branislav Kveton, Csaba Szepesvári, Sharan Vaswani, Zheng Wen, Mohammad Ghavamzadeh, Tor Lattimore

ICML - June 10, 2019

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

Bo Liu, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, Marek Petrik

Journal of Artificial Intelligence Research - May 31, 2019

Optimizing over a Restricted Policy Class in MDPs

Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh, Nikos Vlassis

AISTATS - April 15, 2019

A Block Coordinate Ascent Algorithm for Mean-Variance Optimization

Tengyang Xie, Bo Liu, Yangyang Xu, Mohammad Ghavamzadeh, Yinlam Chow, Daoming Lyu, Daesub Yoon

NeurIPS 2018 - November 30, 2018

A Lyapunov-based Approach to Safe Reinforcement Learning

Yinlam Chow, Ofir Nachum, Mohammad Ghavamzadeh, Edgar Duenez-Guzman

NeurIPS 2018 - November 30, 2018