TOM ZAHAVY

Deep Reinforcement Learning

tomzahavy (at) gmail (dot) com

I am a research scientist at DeepMind in the field of Reinforcement Learning. Previously, I was a Ph.D. candidate at the Technion and interned at Microsoft, Walmart, Facebook, and Google.

My high-level research goal is to build an artificial intelligence via Reinforcement Learning. My prior work focused on aspects of scalability, structure discovery, hierarchy, abstraction, and exploration.

Currently, I focus on Discovery:

Metagradients: building reinforcement learning algorithms that discover an internal knowledge base (hyper parameters, loss function, options, reward), in order to solve the original problem better. You can read more about it in my papers [1,2,3] in this blog post by Robert Lange, in this Podcast (with Robert, Tim, Yanick and myself), or in this talk by David Silver.
Diversity: finding diverse policies that are also nearly optimal in terms maximising reward. I am thinking about this problem through the lens of convex optimisation [1,2,3], that is, suggesting unsupervised convex objectives that lead to diversity as well as RL algorithms that find solutions to this objective via the maximisation of reward.

About me: I come from a small town in 🇮🇱 on the Mediterranean Sea. I am currently living in London 🇬🇧 and I spent some time in the 🇺🇸. My family is coming from 🇩🇪🇮🇩🇱🇺 and by DNA I am 🇮🇩🇭🇺🇮🇷(50/30/20). I am married to Gili, a singer-songwriter from 🇮🇩🇲🇦🇮🇱. I love spending my free time outdoors in camping, hiking, 4X4 driving, mountaineering, skiing, and scuba diving. When I am at home, my hobbies are running, basketball, and reading science-fiction.

News

Feb 21 I was interviewed to the Machine Learning Street Talk podcast, you can listen to it here.
Dec 20 A blog post by Robert Lange is covering my work on meta gradients.
Nov 19 I joined DeepMind as a research scientist.
Oct 19 I finished my Ph.D. at the Technion, advised by Shie Mannor.
Oct 19 I finished a two year internship at Google, working with Yishay Mansour.
Sep 19 I've been chosen as one of the top 400 reviewers at NeurIPS.
Jul 19 I co-organized the third lifelong learning workshop at ICML.