Bruno Castro da Silva

I am an assistant professor in the College of Information and Computer Sciences at the University of Massachusetts and co-Director of the Autonomous Learning Lab.

My research interests are in reinforcement learning (RL), decision making, robotics, and AI safety.

The ultimate goal of my work is to design the necessary tools so that RL algorithms can be widely used to solve challenging real-world tasks in homes and in the workplace, in a safe way, and with as little human intervention as possible.

I am interested, in particular, in two key problems:

• how to design general-purpose RL algorithms capable of autonomously decomposing complex tasks into simpler sub-problems, for which specialized reusable and composable skills be can be learned; and

• how to ensure that these skills are learned in a way that meets user-specified safety requirements with high probability.

These are fundamental questions that underlie the gap between what artificial intelligence agents can—in principle—do and what we can effectively get them to do given our current algorithms.

More broadly, my research interests lie in the intersection of machine learning, reinforcement learning, optimal control theory, and robotics, and include the construction of hierarchical policies, active learning, open-ended learning, biologically-plausible intrinsic motivation mechanisms, Bayesian optimization applied to control, and machine learning algorithms with high-probability safety and fairness guarantees.

Prior to being a professor at UMass, I was an associate professor at the Institute of Informatics at the Federal University of Rio Grande do Sul (UFRGS), in Brazil.

I was a postdoctoral associate at the Aerospace Controls Laboratory at MIT LIDS. I received my Ph.D. in Computer Science from the University of Massachusetts, working under the supervision of Prof. Andrew Barto, in 2014.

I completed my Masters Degree in Computer Science in 2007 under the supervision of Prof. Ana Bazzan at the Federal University of Rio Grande do Sul, in Brazil. I completed my B.S. in Computer Science cum laude at that same university in 2004.

I have worked, in different occasions from 2011 to 2018, as a visiting researcher at the Laboratory of Computational Embodied Neuroscience, in the Istituto di Scienze e Tecnologie della Cognizione, in Rome, developing novel control algorithms for a humanoid robot.

In the Summer of 2014 I worked at Adobe Research, where I developed large-scale optimization techniques for the construction of high-performance features for digital marketing optimization.

From 2011 to 2015 I collaborated with Prof. Victor Lesser on the problem of designing organizationally adept agents and on coordinating learning through emergent distributed supervisory control.