I am a Student Researcher at the Learning Agents Research Group LARG advised by Prof. Peter Stone in the field of Reinforcement Learning (RL). I am interested in working in the field of Natural Language Processing (NLP) and even using RL to solve NLP problems. My previous research includes Maximum Entropy Formulation of RL, Distributional RL, Low Resource Language Dataset Generation, Image Feature Generation and HateSpeech Detection (Paper Presented at AAAI 2021). I have previously interned at Samsung Research Institute in which I worked on a recommender system. I also am a contributor to OpenAI’s gym repository.

My background and history

Research

I am currently involved in research in Reinforcement Learning and Natural Language Processing. I have previously worked in Computer Vision problems for improving the information obtained from an image by introducing a novel image feature based on NLP approaches. My interest is mainly in Conversational AI while I still enjoy exploring new applications for my fields.

Colaboration

I am working with Prof. Peter Stone (University of Texas, Austin) on the maximum entropy formulation of Reinforcement Learning.

I have worked with Prof. Heena Rathore (University of Texas, San Antonio), on distirbutional Reinforcement Learning.

During my Bachelors Degree here I was a part of three labs as an Researcher.

Work Experience

I have worked at:

Education

Bachelor’s Degree (B.E. (Hons.)) in Computer Science at the Birla Institute of Technology and Science, Pilani (BITS Pilani). 2018-2022

I have been a Teaching Assistant for the following Courses:

  • Deep Learning (CS F425)- Selected as one out of two TAs amongst students for the course when it started.
  • Neural Networks and Fuzzy Logic (BITS F312)