I’m on the job market for full-time research scientist positions!

I’m a Research Scientist with Stuart Russell in the Center for Human-Compatible AI at UC Berkeley. My goal is to build robots that operate autonomously/safely in the open world using planning, RL, and LLMs. To do this, I develop formal approaches to decision making for different intelligent systems, including self-driving cars, planetary rovers, satellites, and humanoid robots.

Before that, I completed my PhD in Computer Science under Shlomo Zilberstein in the Resource-Bounded Reasoning Lab at UMass Amherst. My dissertation introduced a range of metareasoning techniques that optimize—particularly monitor and control—the planning and execution processes that compose autonomous systems.

Recently, I’ve won a Distinguished Paper Award at AAAI, received an NSF Graduate Research Fellowship, and was a Distinguished Teaching Award Finalist at UMass Amherst.

  • Marist College

    • BS in Computer Science and Philosophy

    • 4.0 GPA — Valedictorian — NSF Technology Full Scholarship

  • UMass Amherst

    • MS/PhD in Computer Science

    • PhD Candidate with Distinction — NSF Graduate Research Fellowship

News

“Our paper that introduces the online LLM game Tensor Trust received Honorable Mention at ITIF at NeurIPS.”
— December 2023
“ReLM at AAAI accepted our paper that uses self-consistency to calibrate LLMs trained using RLHF.”
— December 2023
“AAMAS accepted our paper on how to formally define deception in decision making.”
— December 2023
“ITIF at NeurIPS accepted our paper that introduces the online LLM game Tensor Trust that we used to build a new prompt injection benchmark dataset.”
— November 2023
“We released an arXiv paper that introduces active teacher selection in RLHF.”
— October 2023
“FMDM at NeurIPS accepted our paper that enables agents to negotiate contracts with each other using LLMs.”
— September 2023
“IROS accepted our paper that formalizes robot architectures as a composition of contract algorithms.”
— June 2023
“I co-organized the CHAI Workshop on AI safety this year.”
— June 2023
“PRL at IJCAI accepted our paper that uses deep RL to learn tree search.”
— June 2023
“We released an arXiv paper that surveys the intersection of fairness and sequential decision making.”
— January 2023
“Our paper on active reward learning from multiple teachers was a Best Paper Award Finalist at SafeAI at AAAI.”
— January 2023
“SafeAI at AAAI accepted our paper on active reward learning from multiple teachers.”
— December 2022
“AIJ accepted our article on competence-aware systems.”
— November 2022
“IROS accepted our paper that uses metareasoning with deep RL to select the partial state abstractions of MDPs.”
— June 2022
“ICAPS accepted our paper that introduces metareasoning with deep RL for hyperparameter tuning of anytime planners.”
— February 2022
“ICRA accepted our paper that introduces metareasoning for safe decision making in autonomous systems.”
— January 2022
“I started a postdoctoral fellowship under Stuart Russell at UC Berkeley.”
— November 2021
“I defended my dissertation.”
— October 2021
“I co-organized the IROS Workshop on Building and Evaluating Ethical Robotic Systems.”
— October 2021
“IROS accepted our paper that introduces an approach to improving competence in autonomous systems.”
— June 2021
“IROS accepted our paper that introduces agent-aware state estimation.”
— June 2021
“HSDIP at ICAPS accepted our paper that introduces metareasoning with deep RL for hyperparameter tuning of anytime planners.”
— June 2021
“R2AW at IJCAI accepted our paper that introduces metareasoning for safe decision making in autonomous systems.”
— May 2021
“AIES accepted our paper that introduces moral communities into ethically compliant sequential decision making.”
— April 2021
“SoCS accepted our paper that investigates the benefits of randomly adjusting the weight of anytime A*.”
— March 2021
“ICRA accepted our paper that introduces an approach to solving large MDPs with partial state abstractions.”
— February 2021
“Our paper that introduces ethically compliant sequential decision making won a Distinguished Paper Award at AAAI.”
— February 2021
“AAAI accepted our paper that introduces ethically compliant sequential decision making.”
— December 2020
“AREA at ECAI accepted our paper that introduces an approach to improving competence in autonomous systems.”
— July 2020
“ECAI accepted my doctoral consortium paper that outlines my dissertation on metareasoning.”
— July 2020
“AISafety at IJCAI accepted our paper that introduces ethically compliant autonomous systems.”
— June 2020
“DynamicSlam at ICRA accepted our paper that introduces agent-aware state estimation.”
— June 2020
“ICRA accepted our paper that introduces model-free metareasoning for determining when to interrupt anytime planners.”
— January 2020
“AAMAS accepted our paper that introduces competence-aware systems.”
— January 2020
“ECAI accepted our paper that integrates decision making and ethics in autonomous systems.”
— January 2020
“IROS accepted our paper that introduces belief space metareasoning for exception recovery.”
— June 2019
“I was a finalist for the Distinguished Teaching Award for teaching assistants.”
— January 2019
“I passed my PhD candidacy qualifier exam with distinction.”
— December 2018
“I’m the primary inventor on a patent for self-driving cars.”
— November 2018
“AEGAP at IJCAI accepted our paper that introduces adaptive metareasoning for bounded rational agents.”
— June 2018
“AI4IoT at IJCAI accepted our paper that introduces belief space planning for information security.”
— May 2018
“IJCAI accepted our paper that introduces model-based metareasoning for determining when to interrupt anytime planners.”
— April 2018
“My advisor and I were awarded an NSF grant on adaptive metareasoning for bounded rational agents.”
— April 2018
“I was awarded an NSF Graduate Research Fellowship.”
— April 2018