Hello there! I'm Jacob Buckman, currently a PhD student at MILA advised by Marc Bellemare and Doina Precup.

My primary research area is deep reinforcement learning. I'm especially interested in unifying theoretical reinforcement learning with practical deep-learning-based algorithms. My current work focuses on finite-sample guarantees and latent-space modeling.

I graduated from Carnegie Mellon University in 2017 with a Bachelor's in computer science and a Master's in Language Technologies, advised by Graham Neubig. From 2017-2018, I was a Google AI Resident in San Francisco.

Website template stolen with love from Desh.