University of Pennsylvania:
MSE in computer science,
graduating in August 2022,
GPA 3.92
Rutgers University:
BS in computer science and mathematics (summa cum laude),
graduated in May 2019,
GPA 3.89
Experience
Research Assistant,
University of Pennsylvania,
September 2019–August 2022
Counterexample-guided Reinforcement Learning
Designed a compositional reinforcement learning algorithm
for a complex task decomposed (by the user) into simpler subtasks
and achieves a higher success rate with less training time
Sped up training and devised a natural framework
for testing the policy
Created a benchmark suite of environments
decomposed into subtasks for running the algorithm
Compositional Learning and Verification of Neural Network Controllers
Designed and trained a neural network policy
that can safely drive in a hallway
with an arbitrary sequence of turns
Internship, Amazon Connect (Amazon Web Services)
Implemented a variation of a feature called least-cost routing,
which sends an outgoing call through the cheapest available carrier
Teaching Assistant,
University of Pennsylvania,
September 2020–May 2021
CIS 519 Applied Machine Learning, fall 2020 semester
CIS 520 Machine Learning, spring 2021 semester
Skills
Machine learning libraries
OpenAI Gym: designing and implementing environments
Stable Baselines: training and evaluating models
Experience with various reinforcement learning algorithms,
including TD3 (Twin Delayed DDPG)
and HER (Hindsight Experience Replay)
Tools
LLVM framework (C++ API)
Coq proof assistant
Z3 theorem prover (C++ and Python APIs)
TLA+ model checker
Programming Languages
Python
C
C++
Java
Standard ML
Courses
Software Engineering (Penn CIS 573, Professor Mayur Naik)
Computer Aided Verification (Penn CIS 573, Professor Rajeev Alur)
Learning for Dynamics and Control (Penn CIS 618, Professor Nikolai Matni)
Software Systems (Penn CIS 505, Profesor Linh Phan)
Software Foundations (Penn CIS 500, Professor Benjamin Pierce)
Machine Learning (Penn CIS 520, Professor Shivani Agarwal)
Publication
Compositional Learning and Verification of Neural Network Controllers,
Emsoft 2021
(PDF)
Radoslav Ivanov, Kishor Jothimurugan,
Steve Hsu, Shaan Vaidya,
Rajeev Alur, and Osbert Bastani
trained a car to drive in a hallway using only LiDAR scans
without access to its true position
proved that the car doesn't crash by modeling the system
as a hybrid automaton
and using a hybrid automaton reachability checker
