Chelsea Finn
cbfinn at cs dot stanford dot edu

I am an Assistant Professor in Computer Science and Electrical Engineering at Stanford University. My lab, IRIS, studies intelligence through robotic interaction at scale, and is affiliated with SAIL and the Statistical ML Group. I also spend time at Google as a part of the Google Brain team.

I am interested in how algorithms can enable machines to acquire more general notions of intelligence through learning and interaction, allowing them to autonomously learn a variety of complex sensorimotor skills in real-world settings. This includes learning deep representations for representing complex skills from raw sensory inputs, enabling machines to learn through interaction without human supervision, and allowing systems to build upon what they've learned previously to acquire new capabilities with small amounts of experience.

Previously, I completed my Ph.D. in computer science at UC Berkeley and my B.S. in electrical engineering and computer science at MIT.

Prospective students and post-docs, please read this before contacting me.

CV  /  Bio  /  PhD Thesis  /  Google Scholar  /  GitHub  /  Twitter

News
Blog Posts
Recent Talk (October 2018)

IRIS Lab
Current PhD students
Frederik Ebert
Suraj Nair
Tianhe Yu
Allan Zhou

Visiting PhD students
Lisa Lee

Teaching

Stanford CS330: Deep Multi-Task and Meta Learning , Fall 2019 - Instructor
UCB CS294-112: Deep Reinforcement Learning , Spring 2017 - Co-Instructor
UCB CS188: Introduction to Artificial Intelligence , Spring 2015 - Graduate Student Instructor (GSI)
MIT 6.S080: Introduction to Inference , Spring 2014 - Teaching Assistant (TA)
MIT 6.141: Robotics: Science and Systems , Spring 2013 - Lab Assistant (LA)
MIT 6.02: Digital Communication Systems , Spring 2012 - Lab Assistant (LA)

Tutorials and Lectures
  • At ICML 2019 and CVPR 2019, I gave an invited tutorial on Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning. Slides, video, and references are linked here.
  • In December 2018, I gave a tutorial on model-based reinforcement learning at the CIFAR LMB program meeting (slides here).
  • At ICML 2017, I gave a tutorial with Sergey Levine on Deep Reinforcement Learning, Decision Making, and Control (slides here, video here).
  • In August 2017, I gave guest lectures on model-based reinforcement learning and inverse reinforcement learning at the Deep RL Bootcamp (slides here and here, videos here and here).
  • In Spring 2017, I co-taught a course on deep reinforcement learning at UC Berkeley. All lecture video and slides are available here.
Invited Talks
Publications

Preprints

Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
Suraj Nair, Chelsea Finn
arXiv / project page / code

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
Frederik Ebert*, Chelsea Finn*, Sudeep Dasari, Annie Xie, Alex Lee, Sergey Levine
arXiv / project page / code / data

Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards
Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog, Mohi Khansari, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn
arXiv / project page

Time Reversal as Self-Supervision
Suraj Nair, Mohammad Babaeizadeh, Chelsea Finn, Sergey Levine, Vikash Kumar
arXiv / project page

Unsupervised Meta-Learning for Reinforcement Learning
Abhishek Gupta, Ben Eysenbach, Chelsea Finn, Sergey Levine
arXiv

2019

RoboNet: Large-Scale Multi-Robot Learning
Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn
Conference on Robot Learning (CoRL), 2019
arXiv / project page, code, data / press

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Tianhe Yu*, Deirdre Quillen*, Zhanpeng He*, Ryan Julian, Karol Hausman, Chelsea Finn, Sergey Levine
Conference on Robot Learning (CoRL), 2019
arXiv / project page / code

Unsupervised Curricula for Visual Meta-Reinforcement Learning
Allan Jabri, Kyle Hsu, Abhishek Gupta, Ben Eysenbach, Sergey Levine, Chelsea Finn
Neural Information Processing Systems (NeurIPS), 2019 (Spotlight)
arXiv (coming soon)

Meta-Learning with Implicit Gradients
Aravind Rajeswaran*, Chelsea Finn*, Sham Kakade, Sergey Levine
Neural Information Processing Systems (NeurIPS), 2019
arXiv / project page

Language as an Abstraction for Hierarchical Reinforcement Learning
YiDing Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn
Neural Information Processing Systems (NeurIPS), 2019
arXiv / project page / code

Guided Meta-Policy Search
Russell Mendonca, Abhishek Gupta, Rosen Kralev, Pieter Abbeel, Sergey Levine, Chelsea Finn
Neural Information Processing Systems (NeurIPS), 2019 (Spotlight)
arXiv / project page / code

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
Lantao Yu*, Tianhe Yu*, Chelsea Finn, Stefano Ermon
Neural Information Processing Systems (NeurIPS), 2019
arXiv

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
Tianhe Yu, Pieter Abbeel, Sergey Levine, Chelsea Finn
International Conference on Intelligent Robots and Systems (IROS), 2019
arXiv / project page

End-to-End Robotic Reinforcement Learning without Reward Engineering
Avi Singh, Larry Yang, Kristian Hartikainen, Chelsea Finn, Sergey Levine
Robotics: Science and Systems (RSS), 2019
arXiv / videos / blog post / code

Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
Annie Xie, Frederik Ebert, Sergey Levine, Chelsea Finn
Robotics: Science and Systems (RSS), 2019
arXiv / videos

Unsupervised Visuomotor Control through Distributional Planning Networks
Tianhe Yu, Gleb Shevchuk, Dorsa Sadigh, Chelsea Finn
Robotics: Science and Systems (RSS), 2019
arXiv / project page

Online Meta-Learning
Chelsea Finn*, Aravind Rajeswaran*, Sham Kakade, Sergey Levine
International Conference on Machine Learning (ICML), 2019
arXiv

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Kate Rakelly*, Aurick Zhou*, Deirdre Quillen, Chelsea Finn, Sergey Levine
International Conference on Machine Learning (ICML), 2019
arXiv / code

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
Kelvin Xu, Ellis Ratner, Anca Dragan, Sergey Levine, Chelsea Finn
International Conference on Machine Learning (ICML), 2019
arXiv

Manipulation by Feel: Touch-Based Control with Deep Predictive Models
Stephen Tian*, Frederik Ebert*, Dinesh Jayaraman, Mayur Mudigonda, Chelsea Finn, Roberto Calandra, Sergey Levine
International Conference on Robotics and Automation (ICRA), 2019
arXiv / videos / blog post

NoRML: No-Reward Meta Learning
Yuxiang Yang, Ken Caluwaerts, Atil Iscen, Jie Tan, Chelsea Finn
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019
arXiv / project page

Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning
Anusha Nagabandi*, Ignasi Clavera*, Simin Liu, Ron Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn
International Conference on Learning Representations (ICLR), 2019
arXiv / videos / code

Unsupervised Learning via Meta-Learning
Kyle Hsu, Sergey Levine, Chelsea Finn
International Conference on Learning Representations (ICLR), 2019
arXiv / project page / code

Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Michael Janner, Sergey Levine, Bill Freeman, Josh Tenenbaum, Chelsea Finn, Jiajun Wu
International Conference on Learning Representations (ICLR), 2019
arXiv / project page

Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL
Anusha Nagabandi, Chelsea Finn, Sergey Levine
International Conference on Learning Representations (ICLR), 2019
arXiv / project page

2018

Stochastic Adversarial Video Prediction
Alex Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, Sergey Levine
arXiv / videos / code

Probabilistic Model-Agnostic Meta-Learning
Chelsea Finn*, Kelvin Xu*, Sergey Levine
Neural Information Processing Systems (NeurIPS), 2018
arXiv / supplementary website

Learning to Learn with Gradients
Chelsea Finn
PhD Dissertation, 2018

Few-Shot Goal Inference for Visuomotor Learning and Planning
Annie Xie, Avi Singh, Sergey Levine, Chelsea Finn
Conference on Learning (CoRL), 2018
arXiv / videos / code

Robustness via Retrying: Closed-Loop Robotic Manipulation via Self-Supervised Learning
Frederik Ebert, Sudeep Dasari, Alex Lee, Sergey Levine, Chelsea Finn
Conference on Learning (CoRL), 2018
arXiv / video

Universal Planning Networks
Aranvind Srinivas, Allan Jabri, Pieter Abbeel, Sergey Levine, Chelsea Finn
International Conference on Machine Learning (ICML), 2018
arXiv / videos / code

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
Tianhe Yu*, Chelsea Finn*, Annie Xie, Sudeep Dasari, Pieter Abbeel, Sergey Levine
Robotics: Science and Systems (RSS), 2018
arXiv / video / code / blog post

Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
Chelsea Finn, Sergey Levine
International Conference on Learning Representations (ICLR), 2018
arXiv

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
Erin Grant, Chelsea Finn, Sergey Levine , Trevor Darrell, Tom Griffiths
International Conference on Learning Representations (ICLR), 2018
arXiv

Stochastic Variational Video Prediction
Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy Campbell, Sergey Levine
International Conference on Learning Representations (ICLR), 2018
arXiv / code / video results

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
Deirdre Quillen*, Eric Jang*, Ofir Nachum*, Chelsea Finn, Julian Ibarz , Sergey Levine
International Conference on Robotics and Automation (ICRA), 2018
arXiv / project page / benchmark code

2017

One-Shot Visual Imitation Learning via Meta-Learning
Chelsea Finn*, Tianhe Yu*, Tianhao Zhang, Pieter Abbeel, Sergey Levine
Conference on Robot Learning (CoRL), 2017 (Long Talk)
Oral presentation at the NIPS 2017 Deep Reinforcement Learning Symposium
arXiv / code / result video / talk video

Self-Supervised Visual Planning with Temporal Skip Connections
Frederik Ebert, Chelsea Finn, Alex Lee, Sergey Levine
Conference on Robot Learning (CoRL), 2017 (Long Talk)
arXiv / code / video results and data

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Chelsea Finn, Pieter Abbeel, Sergey Levine
International Conference on Machine Learning (ICML), 2017
arXiv / blog post / code / video results

Generalizing Skills with Semi-Supervised Reinforcement Learning
Chelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine
International Conference on Learning Representations (ICLR), 2017
arXiv / video results / code

Deep Visual Foresight for Planning Robot Motion
Chelsea Finn, Sergey Levine
International Conference on Robotics and Automation (ICRA), 2017
Best Cognitive Robotics Paper Finalist
arXiv / video

Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States
William Montgomery*, Anurag Ajay*, Chelsea Finn, Pieter Abbeel, Sergey Levine
International Conference on Robotics and Automation (ICRA), 2017
arXiv / video / code

2016

A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
Chelsea Finn*, Paul Christiano*, Pieter Abbeel, Sergey Levine
NIPS Workshop on Adversarial Training, 2016
arXiv

Active One-Shot Learning
Mark Woodward, Chelsea Finn
NIPS Deep Reinforcement Learning Workshop, 2016
arXiv / video description / poster

Unsupervised Learning for Physical Interaction through Video Prediction
Chelsea Finn, Ian Goodfellow, Sergey Levine
Neural Information Processing Systems (NIPS), 2016
arXiv / videos / data / code

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints
Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, Pieter Abbeel, Sergey Levine, Kate Saenko, Trevor Darrell
Workshop on the Algorithmic Foundations of Robotics (WAFR), 2016
arXiv

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
Chelsea Finn, Sergey Levine, Pieter Abbeel
International Conference on Machine Learning (ICML), 2016
Oral presentation at the NIPS 2016 Deep Learning Symposium
arXiv / video results / code / talk video

End-to-End Training of Deep Visuomotor Policies
Sergey Levine*, Chelsea Finn*, Trevor Darrell, Pieter Abbeel
CCC Blue Sky Ideas Award
Journal of Machine Learning Research (JMLR), 2016
arXiv / video / project page / code

Deep Spatial Autoencoders for Visuomotor Learning
Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel
International Conference on Robotics and Automation (ICRA), 2016
arXiv / video

Learning Deep Neural Network Policies with Continuous Memory States
Marvin Zhang, Zoe McCarthy, Chelsea Finn, Sergey Levine, Pieter Abbeel
International Conference on Robotics and Automation (ICRA), 2016
arXiv / video

2015

Bridging text spotting and SLAM with junction features.
Hsueh-Cheng Wang, Chelsea Finn, Liam Paull, Michael Kaess, Ruth Rosenholtz, Seth Teller, John Leonard
International Conference on Intelligent Robots and Systems (IROS), 2015:

Beyond Lowest-Warping Cost Action Selection in Trajectory Transfer
Dylan Hadfield-Menell, Alex X. Lee, Chelsea Finn, Eric Tzeng, Sandy Huang, Pieter Abbeel,
International Conference on Robotics and Automation (ICRA), 2015


This guy makes a nice webpage.