|
I am a Ph.D. student at the Lifelong Machine Learning Group at the University of Pennsylvania, where I am advised by Prof. Eric Eaton. I previously obtained a Master's degree in Robotics from the GRASP Lab at Penn, and got my Bachelor's degree in Electronics Engineering from Universidad Simon Bolivar in Venezuela. I spent the summer of 2021 as a research intern at FAIR NYC working with Arthur Szlam and Ludovic Denoyer on mixture of experts models. Previously, I spent the summer of 2020 as a remote research intern at MSR Montreal working with Harm van Seijen on lifelong learning of compositional reinforcement learning problems. Before that, I spent the summer of 2019 as a research intern at Facebook with the Conversational AI team, working under Alborz Geramifard and co-advised by Mohammad Ghavamzadeh. I also spent a year at Politecnico di Milano in Italy, where I took graduate courses in AI and Robotics, and spent five months at the Advanced Systems Technology group in STMicroelectronics. I am on the academic job market this Fall 2021. Please find here my research, teaching, and diversity statements. Email / CV / Google Scholar / LinkedIn / Twitter |
|
|
I'm interested in the creation of versatile artificially intelligent systems that learn to accumulate knowledge over their lifetimes. I focus on the question of how agents can decompose the complex knowledge required to model a lifelong data stream into simpler units that can be adapted and reused in the future. My work applies these methods to computer vision, robotics, and natural language. |
|
|
|
|
|
We explore the problem of lifelong RL of functionally compositional knowledge, and develop an algorithm that demonstrates zero-shot and forward transfer, avoidance of forgetting, and backward transfer in discrete 2-D and robotic manipulation domains. |
|
We study the question of how to learn compositional parameterized structures from an empirical standpoint, and propose a general-purpose framework that can learn with various forms of knowledge representations and base algorithms. |
|
We introduced an algorithm for directly optimizing factored policies via policy gradients in a lifelong learning setting, and showed theoretically and empirically that our approach avoids catastrophic forgetting. |
|
We introduced the notion of performance gap as a label-dependent notion of domain discrepancy, and developed an boosting-based algorithm, gapBoost, that exploits the insights from gap minimization. |
|
We introduced the problem of lifelong learning from demonstrations, and created an efficient lifelong inverse reinforcement learning (ELIRL) algorithm. |
|
|
|
|
Best paper award. This work was superseded by the NeurIPS version with theoretical results. We introduced an algorithm for directly optimizing factored policies via policy gradients in a lifelong learning setting, and showed empirically that our approach avoids catastrophic forgetting. |
|
|
This work was superseded by the pre-print version with more empirical evidence. We study the question of how to learn compositional parameterized structures from an empirical standpoint, and propose a general-purpose framework that can learn with various forms of knowledge representations and base algorithms. |
|
We developed an architecture for learning multi-domain task oriented dialog policies, based on the notion of action embeddings, which capture domain agnostic representations of how to respond to user's queries. |
|
|
 |
|
|
|