257 citations · 1k across the 96 of their papers we have counts for
7 papers · 1 filter
Intervention Design for Effective Sim2Real Transfer
Melissa Mozifian, Amy Zhang, Joelle Pineau +1
The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal in…
Learning Robust State Abstractions for Hidden-Parameter Block MDPs
Amy Zhang, Shagun Sodhani, Khimya Khetarpal +1
Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this struc…
Learning Invariant Representations for Reinforcement Learning without Reconstruction
Amy Zhang, Rowan McAllister, Roberto Calandra +2
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstructio…
Plan2Vec: Unsupervised Representation Learning by Latent Plans
Ge Yang, Amy Zhang, Ari S. Morcos +3
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 d…
Invariant Causal Prediction for Block MDPs
Amy Zhang, Clare Lyle, Shagun Sodhani +5
Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider the problem o…
Stable Policy Optimization via Off-Policy Divergence Regularization
Ahmed Touati, Amy Zhang, Joelle Pineau +1
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While t…
Out-of-Distribution Generalization via Risk Extrapolation (REx)
David Krueger, Ethan Caballero, Joern-Henrik Jacobsen +5
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that vari…