Last updated October 30, 2021.

My current main research interest is deep reinforcement learning, with a bias towards its applications to robotics. Within that, I care about reducing real-world data needed for robot learning, improving reliability of RL systems, and thinking about problems that arise when applying reinforcement learning to real-world settings.

Asterisks indicate equal contribution.

Papers:


BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning

Eric Jang, Alex Irpan, Mohi Khansari, Daniel Kappler, Frederik Ebert, Corey Lynch, Sergey Levine, Chelsea Finn

Paper: here

CoRL 2021

AW-Opt: Learning Robotic Skills with Imitationand Reinforcement at Scale

Yao Lu, Karol Hausman, Yevgen Chebotar, Mengyuan Yan, Eric Jang, Alexander Herzog, Ted Xiao, Alex Irpan, Mohi Khansari, Dmitry Kalashnikov, Sergey Levine

Paper: here

CoRL 2021

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jake Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, Sergey Levine

Paper: here

Supplementary Video: here

ICML 2021

Meta-Learning Requires Meta-Augmentation

Janarthanan Rajendran*, Alex Irpan*, Eric Jang*

Paper: here

NeurIPS 2020

Scalable Multi-Task Imitation Learning with Autonomous Improvement

Avi Singh, Eric Jang, Alexander Irpan, Daniel Kappler, Murtaza Dalal, Sergey Levine, Mohi Khansari, Chelsea Finn

Paper: here

Supplementary Video: here

ICRA 2020

RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real

Kanishka Rao, Chris Harris, Alex Irpan, Sergey Levine, Julian Ibarz, Mohi Khansari

Paper: here

CVPR 2020

Off-Policy Evaluation via Off-Policy Classification

Alex Irpan, Kanishka Rao, Konstantinos Bousmalis, Chris Harris, Julian Ibarz, Sergey Levine

Paper: here

Code: here

NeurIPS 2019

The Principle of Unchanged Optimality in Reinforcement Learning Generalization

Alex Irpan*, Xingyou Song*

Paper: here

ICML 2019 Workshop, Understanding and Improving Generalization in Deep Learning

Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks

Stephen James, Paul Wohlhart, Mrinal Kalakrishnan, Dmitry Kalashnikov, Alex Irpan, Julian Ibarz, Sergey Levine, Raia Hadsell, Konstantinos Bousmalis

Paper: here

Supplementary Video: here

CVPR 2019

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors

Danijar Hafner, Dustin Tran, Timothy Lillicrap, Alex Irpan, James Davidson

Paper: here

UAI 2019

QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, Sergey Levine

Paper and Video: here

Google AI Blog: here

CoRL 2018, Best Systems Paper

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon Kleinberg

Paper: here

Code: here

ICML 2018

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

Konstantinos Bousmalis*, Alex Irpan*, Paul Wohlhart*, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Laura Downs, Julian Ibarz, Peter Pastor, Kurt Konolige, Sergey Levine, Vincent Vanhoucke

Paper and Video: here

ICRA 2018

Learning Hierarchical Information Flow with Recurrent Neural Modules

Danijar Hafner, Alex Irpan, James Davidson, Nicolas Heess

Paper: here

NeurIPS 2017