Hi there, I’m Rashmeet!
I’m a Ph.D. student in Computer Science advised by Dr. Siddharth Srivastava in the School of Computing and Augmented Intelligence at Arizona State University. I’m a member of the Autonomous Agents and Intelligent Robots (AAIR) research group. I primarily research key Artificial Intelligence principles to help build efficient autonomous sequential decision-making systems. My current research focuses on synthesizing abstractions for transfer in planning and reinforcement learning.
Interests
- Artificial Intelligence
- Autonomous Sequential Decision-making
- Transfer and Generalization in Planning and Reinforcement Learning
- Synthesis and analysis of abstractions
- Probabilistic Reasoning
Education
Ph.D. in Computer Science, 2020 - present
Arizona State University
M.S. in Computer Science, 2018 - 2020
Arizona State University
B.E. in Information Technology, 2013 - 2017
Pune Institute of Computer Technology
Publications
Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning
Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems
Differential Assessment of Black-Box AI Agents
Press
American Astronomical Society awards ASU students Chambliss medals
Rashmeet Kaur Nayyar receives Chambliss medal from American Astronomical Society
Awards
Chambliss Astronomy Achievement Student Award
Experience
Graduate Teaching Assistant
Arizona State University
- Responsible for co‑designing programming assignments in Robot Operating System (ROS), homeworks, & exams for CSE471: Introduction to Artificial Intelligence.
- Created & delivered hands‑on tutorial sessions on topics: Search, Planning, Markov Decision Processes (MDPs), Reinforcement Learning (RL), Statistical Learning, and Probabilistic Inference for a class of 92. Also conducted office hours each week and created rubric for grading homeworks and assignments.
AI Instructor
Clubes De Ciencia Arizona Summer Program
- Taught fundamentals of Artificial Intelligence (Problem Solving by Search, Classical Planning, and Reinforcement Learning) to about 25 high-school students.
- It was particularly challenging to design the course with advanced topics in a manner easily comprehensible to the students.
- Conducted lectures and practical sessions for a week, and received an amazing feedback.
AI ML Engineer Intern
LinkedIn Corporation
- Investigated and proposed a framework for Offline Reinforcement Learning for Task‑oriented Dialogue Agents.
Graduate Research Assistant
Autonomous Agents and Intelligent Robots, Arizona State University
- Researching AI principles to build efficient systems that can reason, plan, & act reliably & safely under uncertainty.
- Co‑developing an AI system for non‑AI experts to help them understand robot planning. Evaluating the system’s integrated task and motion planning on Fetch Robot.
- Proposed a novel method to automatically learn dynamic abstractions that significantly outperform existing methods.
- Learning automatic synthesis of generalized abstract machines/controllers for efficient Reinforcement Learning.
- Proposed a novel method to learn true functionality of adaptive black‑box AI agents to ensure safety.
Graduate Research Assistant
School of Earth and Space Exploration, Arizona State University
- Developed an automated physics-based AI system to reliably detect and identify properties of intergalactic clouds using First-order Open-Universe Probablistic logic in collaboration with Dr. Sanchayeeta Borthakur.
- Explored a Graphical model-based Open-Universe Probabilistic Programming approach developed in Bayesian Logic (BLOG) with inference using Markov Chain Monte Caro methods in Java.
- Analyzed UV Spectra obtained from the Cosmic Origins Spectrograph aboard the Hubble Space Telescope.
Graduate Student Assistant
Arizona State University
- Enriched the learning experience for a class of about 150 students for the course CSE 463: Introduction to Human-Computer Interaction under Dr. Robert Atkinson.
- Responsible for grading, clarifying doubts, and engaging in insightful discussions.
Application Developer
BNY Mellon Technology
- Developed an application from scratch called DORA for the Bank of New York Mellon using a technology stack of Java, AngularJS, Jasmine, Karma, Maven, Grunt, Jenkins, and Kanban agile methodology on NEXEN cloud-based platform.
Research Project Intern
Innobytes Technologies Pvt. Ltd.
- Tackled the problem of inaccurate prediction of tags for audios in MagnaTagATune dataset (Keras, Tensorflow).
- Achieved an AUC-ROC score of 0.886 through CNN & CRNN deep neural network implementations.
Projects
Perfect Observability is a Myth - Restraining Bolts in the Real World
Developed a framework for imposing constraints on an AI agent in a world with nosiy observations. poster attached
Card Shuffling using Markov chains
Evaluated overhand, top-to-random, Knuth, transposition, thorp, and riffle card shuffling techniques. presentation attached
Vision-based Manipulator movement with Fetch
Implemented a visual-feedback based method to guide the Fetch mobile manipulator’s end-effector to reach the target object without using AR-markers. video attached
Higgs Boson Particle discovery
Performed exploratory data analysis, and compared classification of ATLAS experiment events using advanced machine learning techniques such as XGBoost and neural networks.
AI Pacman Agent
Comprehensive implementation of AI methods such as DFS, BFS, UCS, A* search, minimax, expectimax, and alpha-beta pruning to create Pacman in a multi-agent environment using Python.
Denoising and Stacked Autoencoders
Built & evaluated denoising capabilities of a denoising autoencoder with different levels of noise. Trained a stacked autoencoder layer-by-layer in an unsupervised fashion, & fine-tuned the network with the classifier.