Recent News

  • My paper titled “Planning and Learning For Decentralized MDPs With Event Driven Rewards” has been accepted for oral presentation at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).
  • My paper titled “Planning and Learning For Decentralized MDPs With Event Driven Rewards” has also been accepted in the workshop on Planning and Inference at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).
  • [November 2017] I have been awarded Dean’s Academic Merit List (top 5%) fifth consective time in a row.

Conference Publications

AAAI Conference on Artificial Intelligence (AAAI), 2018.

Workshop Publications

. Planning and Learning For Decentralized MDPs With Event Driven Rewards. Workshop on Planning and Inference. AAAI Conference on Artificial Intelligence (AAAI), 2018.

PDF Project

Work Experience

Open Source Contributor, Google Summer of Code 2017
XMPP Standards Foundation [Contributions] [Blog]

Open Source Contributor, Google Summer of Code 2015
XMPP Standards Foundation [Contributions] [Blog]

Graduate Research Assistant, Aug’17 - Present
Machine Learning Lab, KCIS, IIIT Hyderabad

Selected Projects

Security in Multiagent Systems by Policy Randomization

Implemented algorithms to randomize single agent MDPs by maximizing a weighted entropy function and maintaining a certain threshold of reward.

Web Proxy

A simple web proxy that passes requests and data between a web client and a web server.

Cloud Orchestration Layer

Implemented an orchestration of Compute and Storage API which would be provided based on the requirement of the user.

Human Activity Recognition

Classifying human activity recognition amongst six categories using Support Vector Machines and Recurrent Neural Networks (RNNs) with Long Short-Term Memory cells (LSTMs).

AI for Ultimate Tic Tac Toe

Developed an automated AI based player for Ultimate Tic Toe implemented in Python using Greedy Heuristic based Alpha Beta Pruning and optimizing the depth of the search tree.

Planning and Learning For Decentralized MDPs With Event Driven Rewards

Developed novel algorithms for improving the scalability of solving event based Decentralized (PO)MDPs.

Teaching

I have been a Teaching Assistant for the following courses at IIIT Hyderabad:

  • Multi Agent Systems in Monsoon’17

  • Optimization Methods in Spring’17

  • Statistical Methods in Artificial Intelligence (Intro. to Machine Learning) in Monsoon’16

  • Artificial Intelligence in Spring’16

  • Structured System Analysis and Design in Monsoon’15

Resume

My resume is available here.

Contact