Aditya Mohan
Researcher at the Institute of Artificial Intelligence.
I am fascinated by the interplay between the structure of a learning problem and the dynamics of learning algorithms. I believe studying and explicitly utilizing this can help us significantly improve squential decision making techniques, such as Reinforcement Learning. Thus, I am interested in exploring how agents can learn to abstract structure out of tasks and use this to continually adapt to changing scenarios.
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 have previously worked on problems in Robotics, Reinforcement Learning, and Meta-Learning in single-agent and Multi-Agent settings.
Apart from all of the Reinforcement Learning in my life, I also love to sing, play piano and guitar, compose music, dance and cook. Always happy to chat about about anything and everything, so reach out to me if you feel like talking!
news
Jul 4, 2023 |
|
---|
latest posts
Jul 10, 2023 | Policy Gradients |
---|---|
Jul 10, 2023 | Model-Free Control |
Jul 10, 2023 | Model-Free Prediction |