Return Dispersion as an Estimator of Learning Potential for Prioritized Level Replay
Iryna Korshunova, Minqi Jiang, Jack Parker-Holder, Tim Rocktäschel, Edward Grefenstette
People
Edward Grefenstette
Research Scientist
I am a Research Scientist at Facebook AI Research (FAIR), which I joined at the end of 2018, and an Honorary Associate Professor (Reader) at UCL. Previously, I was a Staff Research Scientist at DeepMind. I completed my DPhil (PhD) at the University of Oxford in 2013 under the supervision of Profs Coecke and Pulman, and Dr Sadrzadeh, working on applying category-theoretic tool, initially developed to model quantum information flow, to model compositionality of distributed representations in natural language semantics. My recent research has covered topics at the intersection of deep learning and machine reasoning.
Interests
Machine reasoning, deep learning, natural language understanding
Latest Publications
Deep Reinforcement Learning (Deep RL) Workshop at NeurIPS - 2022
Prioritized Level Replay
Minqi Jiang, Edward Grefenstette, Tim Rocktäschel
Learning with AMIGo: Adversarially Motivated Intrinsic Goals
Andres Campero, Roberta Raileanu, Heinrich Küttler, Joshua B. Tenenbaum, Tim Rocktäschel, Edward Grefenstette
Meta Learning via Learned Loss
Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav S. Sukhatme, Franziska Meier
Learning to Compute Word Embeddings On the Fly
Dzmitry Bahdanau, Tom Bosc, Stanislaw Jastrzebski, Edward Grefenstette, Pascal Vincent, Yoshua Bengio
Learning Reasoning Strategies in End-to-End Differentiable Proving
Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp, Edward Grefenstette, Tim Rocktäschel