My recent past.
I recently (July’17) graduated from The Australian National University(ANU) with a Masters degree in Computer Science, specializing in Artificial Intelligence. My current research interests are in scalable directed exploration for Reinforcement Learning, and AI safety.
I received my Bachelors degree in Electronics and Communication engineering from the University of Kerala, India, back in 2008. Subsequently I joined Infosys Ltd. as a software engineer. The next six years was spent designing and developing software in a wide range of domains. Towards the later years at Infosys, I worked on a proof of concept project that used a Machine Learning algorithm (Fisherfaces) to perform gender classification. This project introduced me to the world of Machine Learning, and subsequently Artificial Intelligence (AI). In June 2014, I resigned from my job and decided to pursue a Masters degree in Computer Science to orient myself with the aspiration to become an AI researcher.
In 2016, during my Masters degree, I participated in the Logic Summer School where I led a team to build Proof Assistant under the supervision of Prof. John Slaney. Proof Assistant is an online platform to enable Logic students to write, verify, and store System L style Natural Deduction proofs for propositional logic. Later in 2016, I joined Prof. Marcus Hutter’s Intelligent Agents research group to work on my Masters research project. The research project was a collaboration project with Jarryd, and was supervised by Prof. Marcus Hutter and Tom Everitt. We introduced a novel optimistic count-based exploration algorithm to perform directed exploration in large Reinforcement Learning problems. Our work was later published as the paper ‘Count-Based Exploration in Feature Space for Reinforcement Learning’ at the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17). Our work was also published as a highlight paper at the Scaling-Up Reinforcement Learning (SURL) workshop conducted as part of ECML PKDD, 2017 conference. My Master’s thesis is an exposition of this work. Below you can see our agent in action, playing Atari games: Freeway, Montezuma’s revenge, Venture, and Qbert.
A full list of my professional projects can be found in my AngelList profile, and my personal projects can be found on Github. The best way to contact me is by email: [email protected]. Feel free to follow me on Twitter, connect with me on LinkedIn, or browse through my CV.