Bruno Castro da Silva

Bruno Castro da Silva is interested in designing reinforcement learning (RL) algorithms that can solve large sets of diverse real-life problems, while ensuring that the learning process is safe according to criteria defined by a designer. To achieve this goal, his research focuses primarily on two key problems: (1) 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 (2) 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. 

The ultimate goal of da Silva's work is to design the necessary tools so that reinforcement learning 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. 

More broadly, da Silva's 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. 

Da Silva joined the faculty of the Manning College of Information and Computer Sciences (CICS) as an assistant professor in 2021. Prior to joining UMass, da Silva was an associate professor at the Institute of Informatics at the Federal University of Rio Grande do Sul (UFRGS), in Brazil. Before that, he worked as a postdoctoral associate at the Aerospace Controls Laboratory at MIT (2015).

Da Silva received his PhD in computer science from the University of Massachusetts Amherst (2014), under the supervision of Prof. Andrew Barto. Both his MSc (2007) and BS cum laude (2004) degrees are in computer science from the Federal University of Rio Grande do Sul, Brazil. Da Silva has worked, on several occasions, as a visiting researcher at the Laboratory of Computational Neuroscience in Rome, developing novel control algorithms for humanoid robots. He has also worked at Adobe Research, in California, developing large-scale machine learning techniques for digital marketing optimization. 

Da Silva has published in top AI, machine learning, and robotics conferences and journals, including ICML, AAAI, IJCAI, and Science. He also received multiple Distinguished Reviewer and Distinguished Senior Program Committee Member awards. Da Silva regularly serves as a senior program committee member and as a reviewer for most premier conferences on machine learning and robotics, including NeurIPS, ICML, AAAI, IJCAI, AAMAS, UAI, IROS, ICRA, ICLR, RLDM, JAIR, and JMLR. He received the Outstanding Teaching Assistant Award in Computer Science; an award granted by the University of Massachusetts and sponsored by Yahoo! for innovations in teaching and training. In addition to his research, da Silva is also passionate about teaching and encouraging women and other underrepresented groups in computer science to pursue STEM careers.