Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

FairVizard: A Visualization System for Assessing Fairness of Ride-Sharing Matching Algorithms

Published in International Conference on Automated Planning and Scheduling (ICAPS), 2021

An interactive visualization system that let users compare different ridesharing-matching algorithms on the basis of different fairness criteria.

A Logic-Based Explanation Generation Framework for Classical and Hybrid Planning Problems

Published in Journal of Artificial Intelligence Research (JAIR), 2022

This paper presents a logic-based explanation generation framework for classical and hybrid planning problems.

VizXP: A Visualization Framework for Conveying Explanations to Users in Model Reconciliation Problems

Published in International Conference on Automated Planning and Scheduling (ICAPS), 2022

This paper presents a visualization framework, VizXP, that allows users to explore the explanations generated by the MRP algorithm.

Using Simple Incentives to Improve Two-Sided Fairness in Ridesharing Systems

Published in International Conference on Automated Planning and Scheduling (ICAPS), 2023

Improving the fairness of ridesharing systems by using a simple, incentive-based approach to improve worse-off groups over time.

DECAF: Learning to be Fair in Multi-Agent Resource Allocation

Published in RL Safety Workshop @Reinforcement Learning Conference (RLC) 2024, 2024

Learning to predict long-term fairness of actions for multi-agent resource allocation with resource constraints.

Urban Ridesharing: Improving Tradeoffs Between Geographic Fairness And Efficiency

Published: October 18, 2022

Abstract: State-of-the-art order dispatching algorithms for ridesharing use deep reinforcement learning techniques along with ILP-based optimization to achieve high efficiency in terms of service rates (proportion of passenger requests accepted). However, in pursuit of efficiency, such approaches might lead to disparity in service rates based on geographic locations, leading to some passenger groups being under-served. In this talk, I present some methods that allow us to improve group-level geographic fairness in such ridesharing systems. We propose an online method that leverages the ILP-based structure of the problem to incorporate fairness into existing matching algorithms without any retraining. Interestingly, we find that it is possible to significantly improve geographic fairness with minimal loss of overall service rate when using our methods.

Learning and Academic Support Centre (LASC)

Academic Support Mentor, Shiv Nadar University, Department of Computer Science and Engineering, 2017

As a mentor for the Learning and Academic Support Centre (LASC), I was responsible for providing assistance to over 100 undergraduate students for the course “Introduction to Computer Science and Programming”. I organized evening study sessions to help students with their coursework and introduced them to concepts in Object Oriented Programming through hands on excercises in C.

Introduction to Artificial Intelligence

Assistant in Instruction, Washington University in St. Louis, Department of Computer Science, 2022

As an assistant in instruction, I was responsible for providing one-on-one assistance to more than 130 students on coursework and homework assignments covering the mathematical foundations and application of algorithms for search, constraint satisfaction, Markov models, reinforcement learning and propositional and first order logic for the course “Introduction to Artificial Intelligence”. I graded homework assignments and exams, and conducted office hours to help students with their coursework. I also delivered guest lectures on Reinforcement Learning and conducted problem-solving sessions on Logic and MDPs.