Ivalin Chobanov

PhD Student

I’m a PhD student working in the area of Reinforcement Learning and Multi-Agent Reinforcement Learning. My research lies in the area of Multi-Agent Reinforcement Learning, with a focus on developing methods that enable agents to exhibit tractable complex behaviours. I am particularly interested in how agents can cooperate effectively in sparse reward settings, interpret and pursue goals, learn continually, and reason across different levels of abstraction.

Tell us about your journey before you joined the Centre for AI in Assistive Autonomy?

Before joining the centre, I worked as a front-office software developer in the finance industry. Prior to that, I completed a Master of Science in Artificial Intelligence at The University of Edinburgh and a Bachelor of Science in Mathematics with Computer Science at The University of Southampton.

What motivates you to work in this area?

As AI continues to advance, we can expect to see many more programs, chatbots, and robots making use of the technology. However, if these agents operate in isolation, their capabilities will remain limited. Just like humans, we can expect them to collaborate in order to solve complex tasks. Enabling such cooperation could unlock a wide range of possibilities that were previously unattainable.

What do you love about Edinburgh?

I love the spirit of the city and how lively it becomes—especially during the Fringe Festival—despite its rich history and age.