I’m a PhD student at the COMO lab. My work concerns the use of Reinforcement Learning in complex environments. I explore applications where robots or software are used for months or years and have to learn (and remember) during this very long period. I’m also very interested in intrinsic motivation, when an agent “plays” and does things not because we ask it to, but because it likes doing it.
Life-Long Hierarchical Reinforcement Learning
Multi-agent Learning Seminar