Abhishek Gupta

I am currently a post-doctoral researcher at MIT, and an affiliate assistant professor in computer science at the Paul G. Allen School at the University of Washington. I will join the department as an assistant professor in Fall 2022. At MIT, I am collaborating with Professor Russ Tedrake and Professor Pulkit Agarwal. I am currently looking for highly motivated students interested in pushing the frontier of robotics and machine learning problems to work with me at UW. Please apply directly through the UW admissions portal, and drop me a line to look through your application.

I completed my PhD in machine learning and robotics at BAIR at UC Berkeley, where I was advised by Professor Sergey Levine and Professor Pieter Abbeel and funded by the NSF GRFP. In a previous life, I completed my bachelors degree at UC Berkeley.

My main research goal is to develop algorithms which enable robotic systems to learn how to perform complex tasks in a variety of unstructured environments. To that end, I work towards building deep reinforcement learning algorithms that can learn in the real world. Recently, I have been specifically focusing on the problems of reward specification, continual real world data collection and learning, offline reinforcement learning for robotics and multi-task learning and dexterous manipulation with robotic hands.

Email  /  CV  /  GitHub  /  Google Scholar  /  Ph.D. Thesis

Workshop Papers and Pre-prints

Ecological Reinforcement Learning
John D Co-Reyes, Suvansh Sanjeev, Glen Berseth, Abhishek Gupta, Sergey Levine
arXiv Preprint

Unsupervised meta-learning for reinforcement learning
Abhishek Gupta*, Benjamin Eysenbach*, Chelsea Finn, Sergey Levine
arXiv preprint, best paper at LLARLA workshop at ICML 2018
paper / blog

Accelerating online reinforcement learning with offline datasets
Ashvin Nair*, Abhishek Gupta*, Murtaza Dalal, Sergey Levine
arXiv preprint

Learning latent state representation for speeding up exploration
Giulia Vezzani, Abhishek Gupta, Lorenzo Natale, Pieter Abbeel
arXiv preprint


Persistent Reinforcement Learning via Subgoal Curricula
Archit Sharma, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn
NeurIPS 2021

Adaptive risk minimization: A meta-learning approach for tackling group shift
Marvin Zhang, Henrik Marklund, Nikita Dhawan, Abhishek Gupta, Sergey Levine, Chelsea Finn
NeurIPS 2021
paper / blog

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Kate Rakelly, Abhishek Gupta, Carlos Florensa, Sergey Levine
NeurIPS 2021

Fully Autonomous Real-World Reinforcement Learning for Mobile Manipulation
Charles Sun, Jedrzej Orbik, Coline Devin, Brian Yang, Abhishek Gupta, Glen Berseth, Sergey Levine
CoRL 2021

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
Kevin Li*, Abhishek Gupta*, Ashwin D Reddy, Vitchyr Pong, Aurick Zhou, Justin Yu, Sergey Levine
ICML 2021
paper / website

Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention
Abhishek Gupta*, Justin Yu*, Tony Z. Zhao*, Vikash Kumar*, Aaron Rovinsky, Kelvin Xu, Thomas Devlin, Sergey Levine
ICRA 2021
paper / website

ROBEL: RObotics BEnchmarks for Learning with low-cost robots
Michael Ahn, Henry Zhu, Kristian Hartikainen, Hugo Ponte, Abhishek Gupta, Sergey Levine, Vikash Kumar
CoRL 2019
paper / blog

The ingredients of real-world robotic reinforcement learning
Henry Zhu*, Justin Yu*, Abhishek Gupta*, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine
ICLR 2020 (spotlight)
paper / blog

Discor: Corrective feedback in reinforcement learning via distribution correction
Aviral Kumar, Abhishek Gupta, Sergey Levine
NeurIPS 2020 (spotlight)
paper / blo

Gradient surgery for multi-task learning
Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn
NeurIPS 2020

Learning to reach goals via iterated supervised learning
Dibya Ghosh*, Abhishek Gupta*, Ashwin Reddy, Justin Fu, Coline Devin, Benjamin Eysenbach, Sergey Levine
ICLR 2021 (Oral)
paper / blog

Unsupervised curricula for visual meta-reinforcement learning
Allan Jabri, Kyle Hsu, Benjamin Eysenbach, Abhishek Gupta, Alexei Efros, Sergey Levine, Chelsea Finn
NeurIPS 2019 (spotlight)

Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning
Abhishek Gupta, Vikash Kumar, Corey Lynch, Sergey Levine, Karol Hausman
CORL 2019
paper / website

Guided meta-policy search
Russell Mendonca, Abhishek Gupta, Rosen Kralev, Pieter Abbeel, Sergey Levine, Chelsea Finn
NeurIPS 2019 (spotlight)

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
Henry Zhu*, Abhishek Gupta*, Aravind Rajeswaran, Sergey Levine, Vikash Kumar
ICRA 2019
paper / blog

Guiding policies with language via meta-learning
John D Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, Sergey Levine
ICLR 2019

Learning actionable representations with goal-conditioned policies
Dibya Ghosh, Abhishek Gupta, Sergey Levine
ICLR 2019

Automatically composing representation transformations as a means for generalization
Michael B. Chang, Abhishek Gupta, Sergey Levine, Thomas Griffith
ICLR 2019

Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings
John D Co-Reyes*, YuXuan Liu*, Abhishek Gupta*, Benjamin Eysenbach, Pieter Abbeel, Sergey Levine
ICML 2018

Imitation from observation: Learning to imitate behaviors from raw video via context translation
YuXuan Liu*, Abhishek Gupta*, Pieter Abbeel, Sergey Levine
ICRA 2018
paper / video

Meta-reinforcement learning of structured exploration strategies
Abhishek Gupta, Russell Mendonca, YuXuan Liu, Pieter Abbeel, Sergey Levine
NeurIPS 2018 (spotlight)
paper / code

Diversity is all you need: Learning skills without a reward function
Benjamin Eysenbach, Abhishek Gupta, Julian Ibarz, Sergey Levine
ICLR 2019
paper / video

Learning complex dexterous manipulation with deep reinforcement learning and demonstrations
Aravind Rajeswaran*, Vikash Kumar*, Abhishek Gupta, Giulia Vezzanni, John Schulman, Emanuel Todorov, Sergey Levine
RSS 2018
paper / video

Learning modular neural network policies for multi-task and multi-robot transfer
Abhishek Gupta*, Coline Devin*, Trevor Darrell, Pieter Abbeel, Sergey Levine
ICRA 2017
paper / video

Learning invariant feature spaces to transfer skills with reinforcement learning
Abhishek Gupta*, Coline Devin*, Yuxuan Liu, Pieter Abbeel, Sergey Levine
ICLR 2017
paper / video

Learning dexterous manipulation for a soft robotic hand from human demonstrations
Abhishek Gupta, Clemens Eppner, Sergey Levine, Pieter Abbeel
IROS 2016
paper / video

Guided search for task and motion plans using learned heuristics
Rohan Chitnis, Dylan Hadfield-Menell, Abhishek Gupta, Siddhart Srivastava, Edward Groshev, Christopher Lin, Pieter Abbeel
ICRA 2016
paper / video

Learning from multiple demonstrations using trajectory-aware non-rigid registration with applications to deformable object manipulation
Alex Lee, Abhishek Gupta, Henry Lu, Sergey Levine, Pieter Abbeel
IROS 2015

Learning force-based manipulation of deformable objects from multiple demonstrations
Alex X. Lee, Henry Lu, Abhishek Gupta, Sergey Levine, Pieter Abbeel
ICRA 2015

Tractability of planning with loops
Siddharth Srivastava, Shlomo Zilberstein, Abhishek Gupta, Pieter Abbeel, Stuart Russell
AAAI 2015
paper / video

Website template from Jon Barron.
Last updated January 2021.