Hello! I am a master's student in the lab. Before joining the lab, I completed my undergraduate degree at McGill, majoring in neuroscience.
I am mainly interested in most things reinforcement learning (RL) related. RL is quite a fascinating area to work on - both for its connection to purely engineering fields, and also as a "complete" model for intelligence, encompassing both action and perception.
Currently, I am working on how RL agents learn in partially observable settings, and how machine learning methods for these settings (e.g. recurrent neural nets) affect the learning process. More broadly speaking, I am curious about how we might get artificial agents to work in similar settings as faced by animals (and humans), such as tasks that require the use of long term memories, and how we might map these algorithmic components back to neurobiology.