Amy Zhang

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

June 10, 2020

RESEARCH

Plan2vec: Unsupervised Representation Learning by Latent Plans

In this paper we introduce plan2vec, an unsupervised representation learning approach that is inspired by reinforcement learning. Plan2vec constructs a weighted graph on an image dataset using near-neighbor distances, and then extrapolates this local metric…

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

June 10, 2020

July 09, 2018

RESEARCH

Composable Planning with Attributes

The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning how its actions affect those properties, it may be able to use…

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

July 09, 2018

July 14, 2020

ML APPLICATIONS

RESEARCH

Invariant Causal Prediction for Block MDPs

Generalization across environments is critical for the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider…

Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup

July 14, 2020