Publications

Reinforcement Learning with Prototypical Representations
Task-Agnostic Morphology Evolution
Self-Supervised Policy Adaptation during Deployment
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
Visual Imitation Made Easy
Robust Policies via Mid-Level Visual Representations
Reinforcement Learning with Augmented Data
Generalized Hindsight for Reinforcement Learning
Swoosh! Rattle! Thump! - Actions that Sound
Learning to Manipulate Deformable Objects without Demonstrations
Discovering Motor Programs by Recomposing Demonstrations
Robot Learning via Human Adversarial Games
PyRobot: An Open-source Robotics Framework for Research and Benchmarking
Environment Probing Interaction Policies
Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias
Asymmetric Actor Critic for Image-Based Robot Learning
CASSL: Curriculum Accelerated Self-Supervised Learning
Learning to Fly by Crashing
Robust Adversarial Reinforcement Learning
The Curious Robot: Learning Visual Representations via Physical Interactions