Amy Zhang

DATA SCIENTIST | MONTREAL, CANADA

Amy is a data scientist at Facebook. She is a final year PhD candidate at McGill University and the Mila Institute, co-supervised by Joelle Pineau and Doina Precup. Amy is currently working on state abstractions and learning representations for generalization in reinforcement learning. She holds a M.Eng. in EECS and dual B.Sci. degrees in Mathematics and EECS from MIT.

Amy's Publications

July 01, 2022

Denoised MDPs: Learning World Models Better Than the World Itself

Yuandong Tian, Amy Zhang, Simon Shaolei Du, Antonio Torralba, Phillip Isola, Tongzhou Wang

July 01, 2022

June 09, 2022

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Amy Zhang, Ashvin Nair, Patrick Yin, Philippe Hansen-Estruch, Sergey Levine

June 09, 2022

December 03, 2021

Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Amy Zhang, Aviral Kumar, Dibya Ghosh, Jad Rahme, Ryan Adams, Sergey Levine

December 03, 2021

April 20, 2021

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

Luis Pineda, Amy Zhang, Brandon Amos, Roberto Calandra, Nathan Lambert

April 20, 2021

May 08, 2020

RESEARCH

Plan2vec: Unsupervised Representation Learning by Latent Plans

Roberto Calandra, Amy Zhang, Ari Morcos, Joelle Pineau, Ge Yang, Pieter Abbeel

May 08, 2020

July 09, 2018

RESEARCH

Composable Planning with Attributes

Adam Lerer, Amy Zhang, Arthur Szlam, Rob Fergus, Sainbayar Sukhbaatar

July 09, 2018