Portrait of Pablo Samuel Castro

Pablo Samuel Castro

Core Industry Member
pablo-samuel.castro@mila.quebec
Adjunct professor, Université de Montréal, Department of Computer Science and Operations Research
Research Scientist, Google DeepMind
Website
Google Scholar
LinkedIn
X

Biography

Pablo Samuel Castro was born and raised in Quito, Ecuador, and moved to Montréal after high school to study at McGill University. For his PhD, he studied reinforcement learning with Doina Precup and Prakash Panangaden at McGill. Castro has been working at Google for over eleven years. He is currently a staff research scientist at Google DeepMind in Montreal, where he conducts fundamental reinforcement learning research and is a regular advocate for increasing LatinX representation in the research community.

He is also an adjunct professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. In addition to his interest in coding, AI and math, Castro is an active musician.

Current Students

Ayoub Echchahed
Master's Research - Université de Montréal
ayoub.echchahed@mila.quebec
Website
Samuel Garcin
Collaborating researcher
samuel.garcin@mila.quebec
Website
Github
Google Scholar
Johan Samir Obando Ceron
PhD - Université de Montréal
Principal supervisor :
Aaron Courville
johan.ceron@mila.quebec
Github
Google Scholar
Gandharv Patil
PhD - McGill University
Principal supervisor :
Doina Precup
patilgan@mila.quebec
Website
Github
Google Scholar

Publications

A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc Gendron-Bellemare
Will Dabney
Robert Dadashi
Adrien Ali Taiga
Pablo Samuel Castro
Nicolas Le Roux
Dale Schuurmans
Tor Lattimore
Clare Lyle
We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functi… (see more)ons. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary policies for a given environment. We show that this optimization reduces to making accurate predictions regarding a special class of value functions which we call adversarial value functions (AVFs). We demonstrate that using value functions as auxiliary tasks corresponds to an expected-error relaxation of our formulation, with AVFs a natural candidate, and identify a close relationship with proto-value functions (Mahadevan, 2005). We highlight characteristics of AVFs and their usefulness as auxiliary tasks in a series of experiments on the four-room domain.
arxiv.org
Dopamine: A Research Framework for Deep Reinforcement Learning
Pablo Samuel Castro
Subhodeep Moitra
Carles Gelada
Saurabh Kumar
Marc Gendron-Bellemare
Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provid… (see more)e stable, comprehensive implementations for benchmarking. At the same time, recent deep RL research has become more diverse in its goals. In this paper we introduce Dopamine, a new research framework for deep RL that aims to support some of that diversity. Dopamine is open-source, TensorFlow-based, and provides compact and reliable implementations of some state-of-the-art deep RL agents. We complement this offering with a taxonomy of the different research objectives in deep RL research. While by no means exhaustive, our analysis highlights the heterogeneity of research in the field, and the value of frameworks such as ours.
2018-09-27
ArXiv (preprint)
arxiv.org
arxiv.org