Aditya Mohan

Sequential decision-making problems in the real world often come with structure that is typically underutilized in Reinforcement Learning (RL). I develop methods that enable RL agents to utilize information about contextual changes, temporal dependencies, and modular decompositions, in order to help them learn efficiently and adapt to changing but structured environments. My research spans areas such as Contextual RL, Meta-RL, AutoRL, and Representation Learning, and I am currently working on self-supervised RL, where the agent learns behavior without explicit labels or human supervision.

Before my PhD: I completed my Master’s in Autonomous Systems from Technical University of Berlin and EURECOM, where my thesis focused on ad-hoc cooperation in Hanabi. I did a Bachelor’s in Electronics and Communications Engineering from Manipal Institute of Technology, and worked for a year as a Risk Consultant with KPMG before starting my Master studies.

Beyond Research: I have a passion for singing, playing piano and guitar, composing music (Here’s a link to some music videos that I occasionally put up: https://www.instagram.com/melodic.musings/). I also enjoy cooking, reading up on a variety of topics and dancing. If you’d like to chat about research, music, food, or anything else, don’t hesitate to book a slot in my calender