Portrait of Vincent Taboga

Vincent Taboga

Lab Representative
Postdoc
Research Topics
Deep Learning
Dynamical Systems
Optimization
Reinforcement Learning

Biography

I'm a postdoc at Mila working on Reinforcement Learning and Optimal Control applied to real-world problems. I'm particularly interested in the optimal control of energy systems, to mitigate the impacts of climate change. Prior to my postdoc, I have done my Ph.D. at Polytechnique and Mila on the optimization of heating and cooling systems in buildings.

When I'm not thinking about heating systems, I'm passionate about sports. After swimming competitively for many years, I turned my attention to rock climbing a few years ago. I also love making pizza.

Publications

What Matters when Modeling Human Behavior using Imitation Learning?
As AI systems become increasingly embedded in human decision-making process, aligning their behavior with human values is critical to ensuri… (see more)ng safe and trustworthy deployment. A central approach to AI Alignment called Imitation Learning (IL), trains a learner to directly mimic desirable human behaviors from expert demonstrations. However, standard IL methods assume that (1) experts act to optimize expected returns; (2) expert policies are Markovian. Both assumptions are inconsistent with empirical findings from behavioral economics, according to which humans are (1) risk-sensitive; and (2) make decisions based on past experience. In this work, we examine the implications of risk sensitivity for IL and show that standard approaches do not capture all optimal policies under risk-sensitive decision criteria. By characterizing these expert policies, we identify key limitations of existing IL algorithms in replicating expert performance in risk-sensitive settings. Our findings underscore the need for new IL frameworks that account for both risk-aware preferences and temporal dependencies to faithfully align AI behavior with human experts.
A Distributed ADMM-Based Deep Learning Approach for Thermal Control in Multi-Zone Buildings Under Demand Response Events.
A Distributed ADMM-based Deep Learning Approach for Thermal Control in Multi-Zone Buildings
The surge in electricity use, coupled with the dependency on intermittent renewable energy sources, poses significant hurdles to effectively… (see more) managing power grids, particularly during times of peak demand. Demand Response programs and energy conservation measures are essential to operate energy grids while ensuring a responsible use of our resources This research combines distributed optimization using ADMM with Deep Learning models to plan indoor temperature setpoints effectively. A two-layer hierarchical structure is used, with a central building coordinator at the upper layer and local controllers at the thermal zone layer. The coordinator must limit the building's maximum power by translating the building's total power to local power targets for each zone. Local controllers can modify the temperature setpoints to meet the local power targets. The resulting control algorithm, called Distributed Planning Networks, is designed to be both adaptable and scalable to many types of buildings, tackling two of the main challenges in the development of such systems. The proposed approach is tested on an 18-zone building modeled in EnergyPlus. The algorithm successfully manages Demand Response peak events.
Neural differential equations for temperature control in buildings under demand response programs
Neural differential equations for temperature control in buildings under demand response programs