Rashmeet Kaur Nayyar

Ph.D., Computer Science

Arizona State University

Hi there, I’m Rashmeet!

I’m a Computer Science Ph.D. student working with 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 study Reinforcement Learning (RL) with the goal of building efficient autonomous sequential decision-making systems that solve long-horizon problems. Currently, I am focussed on automatically synthesizing temporal and state abstractions for transfer in RL and interleaving planning with RL.

Interests

Learning Abstractions for Transfer and Generalization in RL
Long‐horizon Planning under Uncertainty
Autonomous Sequential Decision‐making
Robotics

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

Conditional Abstraction Trees for Sample-efficient Reinforcement Learning

In many real-world problems, the learning agent needs to learn a problem’s abstractions and solution simultaneously. However, most such …

Mehdi Dadvar, Rashmeet Kaur Nayyar, Siddharth Srivastava

PDF DOI Link

Conditional Abstraction Trees for Sample-efficient Reinforcement Learning

Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems

Several goal-oriented problems in the real-worldcan be naturally expressed as Stochastic ShortestPath Problems (SSPs). …

Rushang Karia, Rashmeet Kaur Nayyar, Siddharth Srivastava

PDF DOI Link

Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems

Differential Assessment of Black-Box AI Agents

Much of the research on learning symbolic models of AIagents focuses on agents with stationary models. This …

Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava

PDF DOI Link

Differential Assessment of Black-Box AI Agents

Physics-based Detection and Identification of Intergalactic clouds using Probabilistic Programming

In this talk, I present a poster on my collaborative interdisciplinary research on using first-order probabilistic logic for inferring properties of intergalactic space.

Rashmeet Nayyar, Mansi Padave, Sanchayeeta Borthakur, Siddharth Srivastava

Poster Link

Physics-based Detection and Identification of Intergalactic clouds using Probabilistic Programming

Content-based auto-tagging of audios using deep learning

In the recent years, deep learning and feature learning have drawn significant attention in the field of Music Information Retrieval …

Rashmeet Nayyar, Sushmita Nair, Omkar Patil, Rasika Pawar, Amruta Lolage

PDF DOI Link

Content-based auto-tagging of audios using deep learning

Press

American Astronomical Society awards ASU students Chambliss medals

Karin Valentine, ASU NOW, May 2020.

Rashmeet Kaur Nayyar receives Chambliss medal from American Astronomical Society

Erik Wirtanen, ASU Inner Circle, June 2020.

Awards

Chambliss Astronomy Achievement Student Award

American Astronomical Society Apr 2020

Awarded among 6 graduate medal winners chosen from hundreds of students nationwide for my interdisciplinary research.

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.