Chelsea Finn
cbfinn at cs dot stanford dot edu

I am an Assistant Professor in the Computer Science Department at Stanford University. I also spend time at Google Brain.

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.

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

• In Fall 2019, I will be teaching a new course on deep multi-task and meta learning.
• I am honored and thrilled to have received the ACM 2018 Doctoral Dissertation Award for my thesis, Learning to Learn with Gradients.
• Our work on enabling robots to use objects as tools was featured in an article by MIT Technology Review
• I am honored to have received the MIT TR35 pioneer award.
• In August 2018, I completed my PhD!
• Some of my research was featured in a TechCrunch article.
• At NIPS 2017, we showcased our research on meta-imitation learning and visual foresight in a live robot demo! For more information and a video, see this page.
• In summer 2017, I co-organized BAIR camp, a 2-day summer camp on human-centered AI for high-school students from low income backgrounds. We are organizing a second camp in August 2018.
• show more
In Spring 2017, I helped develop and co-taught a course on deep reinforcement learning.
I co-organized a workshop at NIPS 2016 on Deep Learning for Action and Interaction (videos here).
My colleagues and I have released the robotic grasping and pushing data used in Levine et al. '16 (ISER) and Finn et al. '16 (NIPS): Google Brain Robotics Data.

• End-to-End Deep Reinforcement Learning without Reward Engineering: how robots can learn skills end-to-end from pixels without reward engineering.
• Robots that Learn to Use Improvised Tools: how robots can figure out how to solve tasks using tools, including unconventional tools, by learning from a combination of unsupervised interaction and example demonstrations.
• Manipulation By Feel: how we can use visual foresight to enable robots to manipulate objects entirely by feel without vision.
• Visual Model-Based Reinforcement Learning as a Path towards Generalist Robots: overviews our work on learning a single model that can be used to accomplish many different tasks, without requiring human supervision.
• One-Shot Imitation from Watching Videos: describes our work on enabling robots to learn to manipulate new objects by watching humans.
• Learning to Learn: covers recent approaches to meta-learning and our recent paper on model-agnostic meta-learning. It was also translated into Chinese.
• How Robots Can Acquire New Skills from Their Shared Experience: features some work done by me and my colleagues at Google Brain, X, and DeepMind on learning across multiple robots. It was nicely summarized by the MIT Technology Review here.

• 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.

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)