I'm a fourth year grad student at UMass Amherst working in the Resource-Bounded Reasoning Lab under Dr. Shlomo Zilberstein. My research focuses mainly on problems in automated reasoning. I currently work on metareasoning techniques that enable autonomous systems to optimize their own process of deliberation. I also work on computational approaches to safety that allow autonomous systems to reason about and learn from exceptional circumstances that may occur during normal operation. Before coming to grad school, I worked as a software developer on Wall Street. Outside of all of that, I'm interested in many problems in philosophy, especially free will, mind, metaphysics, and epistemology.


University of Massachusetts Amherst
MS/PhD in Computer Science Expected Aug 2022
Dr. Shlomo Zilberstein Resource-Bounded Reasoning Lab Artificial Intelligence Research
Marist College
BS in Computer Science and Philosophy with a Minor in Mathematics May 2014
4.0 GPA Valedictorian Summa Cumme Laude


Jan 2020 ICRA accepted our paper that uses metareasoning with reinforcement learning to determine when to stop anytime algorithms! Jan 2020 AAMAS accepted our paper that learns how to optimize autonomy in competence-aware systems! Jan 2020 ECAI accepted our paper that offers an integrated approach to decision making and ethics in moral autonomous systems! June 2019 IROS accepted our paper that uses belief space metareasoning for exception recovery in autonomous systems! Jan 2019 I was a finalist for the Distinguished Teaching Award for teaching assistants. Dec 2018 I passed my qualifying exam with distinction! I'm a PhD candidate now. Nov 2018 I'm the primary inventor on a patent application for self-driving cars! June 2018 The AEGAP workshop at IJCAI accepted our paper that introduces adaptive metareasoning. May 2018 The AI4IoT workshop at IJCAI accepted our paper that applies belief-space planning to information security. April 2018 IJCAI accepted our paper that uses metareasoning to determine when to stop anytime algorithms! April 2018 My advisor and I received funding for our NSF grant on adaptive metareasoning! April 2018 I was awarded an NSF Graduate Research Fellowship! Check out the article. Feb 2018 I got an internship with Nissan Research this summer! I'll be working on their self-driving cars. July 2017 I wrote another post on how to compose music with deep learning. July 2017 I wrote my first blog post! It covers the basics of MDPs. June 2017 I attended the 50 Years of the ACM Turing Award Celebration as a Student Scholar in San Francisco after being awarded a SIGAI travel grant. May 2017 I attended the 1st Summer School on Cognitive Robotics hosted by MERS at MIT. Dec 2016 Sam Witty and I presented our report and our poster on Deep Jammer at UMass Amherst. Aug 2016 I was awarded the Victor Lesser Graduate Scholarship in Artificial Intelligence. June 2016 I started my MS/PhD in Computer Science at UMass Amherst.


2016 – Now UMass Amherst MS/PhD Student in Computer Science Summer 2018 Nissan Research Intern in Autonomous Driving 2015 – 2016 Goldman Sachs Software Developer in Big Data 2015 – 2016 Marist College Research Assistant in Distributed Graph Databases 2014 – 2015 Goldman Sachs Software Developer in Network Engineering 2013 – 2015 Marist College Software Developer in Stimulus-Response Testing 2013 – 2014 OmniTech Software Developer in Machine Learning 2012 – 2014 Goldman Sachs Software Developer Intern in Network Engineering 2010 – 2012 Marist College Web Developer at www.marist.edu Summer 2011 Marist College Teaching Assistant at the Summer Game Design Institute 2010 – 2014 Marist College Double Major in Computer Science and Philosophy with a minor in Mathematics


Belief Space Metareasoning for Exception Recovery

IROS 2019 Justin Svegliato et al.

Autonomous systems use decision-making models that rely on simplifying assumptions to reduce the complexity of the real world. However, as a result of their assumptions, these systems may encounter a wide range of exceptions. Our paper offers a new type of autonomous system, called an introspective autonomous system, that resolves exceptions by interleaving regular decision making with exception handling based on a belief over whether or not any exceptions have been encountered during operation.

Source: Our Paper

Meta-Level Control of Anytime Algorithms with Online Performance Prediction

IJCAI 2018 Justin Svegliato, Kyle Wray, Shlomo Zilberstein

We develop a meta-level control technique to determine the point at which a robot should stop thinking and start doing. In dynamic environments, a robot rarely has enough time to determine the optimal solution to a decision-making problem. To handle this limitation, a robot can use an anytime algorithm, which is a type of algorithm that slowly improves a solution over time. This means that as the robot thinks more and more, the solution slowly gets better and better. Now here's the question: how long should the robot think for? That's what we answer in this paper.

Distributed Graph Snapshot Placement and Query Performance in a Data Center Environment

CSCI 2015 Alan Labouseur, Justin Svegliato, Jeong-Hyon Hwang

We investigate how to best place the vertices of graph snapshots across workers in a distributed dynamic graph database to speed up queries like PageRank and average degree. By extending G*, our own distributed dynamic graph database, we examine how each query performs when the vertices of a set of graph snapshots are placed on a single worker or spread across all of the workers. It turns out that vertex placement has a big impact on query performance.

OpenSR: An Open-Source Stimulus-Response Testing Framework

Human Technology 2015 RCIS 2013 Carolyn Matheus, Justin Svegliato

We present OpenSR, an open source stimulus-response testing framework. In our framework, you can create, manage, and track an implicit association test (IAT). Basically, an IAT can help researchers determine whether or not someone has an implicit bias for or against something. Since most researchers currently have to buy complicated, expensive software to do this, we built a free, easy-to-use, customizable alternative that's better than what's already on the market.

Source: OpenSR


Deep Jammer

Justin Svegliato, Sam Witty

We built Deep Jammer, a music generator that learns how to compose classical music by listening to 320 classical piano pieces. By using deep learning, specifically two LSTMs, it can learn the spatial and temporal patterns of classical music. In a survey of over 50 participants, the classical piano pieces composed by Deep Jammer scored a 7.5 rating compared to a piece by Bach that scored an 8.1 rating. Finally, to experiment with transfer learning, we trained Deep Jammer on just twenty jazz piano pieces. While it wasn't perfect, it quicky picked up on the rhythm and sound of jazz.

Source: Colah's Blog


Justin Svegliato

To learn more about automated decision-making, I built Logos, a library that can solve MDPs. Logos offers dynamic programming methods like value iteration and policy iteration and reinforcement learning algorithms like Monte Carlo learning and TD learning. I currently use Logos in semi-autonomous system simulations to control a self-driving car and a reinforcement learning agent that learns how to optimally play tic-tac-toe by playing games against itself.

Source: Wikipedia

Deep Rainbow

Justin Svegliato, Martin Mena

We built an optimal Rubik’s Cube solver, Deep Rainbow, that uses IDA*. We used an admissible heuristic based on three disjoint pattern databases where each database is associated with the set of edge cubees and two different sets of corner cubees. We based our solver on Richard Korf’s approach. In just a few minutes, Deep Rainbow can find optimal solutions to problems that are twelve steps or less away from the goal.

Shallow Blue

Justin Svegliato, Martin Mena

We built a chess agent named Shallow Blue that uses minimax with alpha-beta pruning. The evaluation function incorporates many important dimensions of chess, such as piece development, material balance, mobility, and attack range. Luckily, Shallow Blue won a chess tournament that had over fifteen teams that built their own chess agents. To add to the fun, I also built a Connect Four agent and a Tic-Tac-Toe agent using a similar method.

Source: Wikipedia


Justin Svegliato

In an awesome class (CMPT 424) taught by Dr. Alan Labouseur, I built SvegOS, a browser-based operating system from scratch. Just like any Unix operating system, you can manage files (create, read, update, delete, and ls), load a program (load), manage processes (run, ps, and kill), and a lot more. To top it all off, the interface shows the CPU registers, the memory, the hard drive, and the state of every process, so you can follow my operating system as it runs.


Justin Svegliato

In another great class (CMPT 432) taught by Dr. Alan Labouseur, I built Svegliator, a compiler that compiles a C-like language into 6502alan assembly language. The compiler shows the resulting machine code, the concrete syntax tree, the abstract syntax tree, and the symbol table. Just so you can trace exactly what the compiler is doing, it records each step of the scanner, the parser, the semantic analyzer, and the code generator during compilation.

Source: My Compiler



Awarded to the top graduating student

National Science Foundation Graduate Research Fellowship

Awarded to high-potential grad students early in their career

National Science Foundation Scholarship

Included a full scholarship for every year of college

Excellence Award in Computer Science

Awarded to the top graduating student in computer science

Excellence Award in Philosophy

Awarded to the top graduating student in philosophy

Intern of the Year

Awarded to a graduating student for excellence in industry

Summa Cum Laude

Awarded to students with at least a 3.85 GPA

Victor Lessor Graduate Scholarship in Artificial Intelligence

Awarded to a top incoming grad student in artificial intelligence

SIGAI Student Scholar

Included a grant for the 50 Years of the ACM Turing Award Celebration

Deans’ Circle (2010 – 2014)

Admitted to an honors organization of only the top 3% of students

Deans’ List (2010 – 2014)

Awarded to students with at least a 3.6 GPA

Fiovranti Memorial Scholarship for Athletics

Awarded for excellence in cross country and track and field

Marist Presidential Scholar Student Speaker

Selected to give a talk to the top accepted prospective students