Nathan is a researcher, athlete, writer, and mental-health advocate.

Featured Posts:

A Different Intro to RL in 30 Minutes

Reflecting on being a graduate student (in AI) in 2020

All grad students (should) study graphic design

Built with Webflow

Thoughtfully deployed robots that learn to interact in many real world environments.

Robotics

Intelligent & novel devices to interact with the physical world.

Machine Learning

The science of using data to make decisions in the presence of uncertainty.

Society

Making sure the stakeholders of automation are in the conversation.

My research experience

I'm interested in the intersection of machine learning and control, with applications to experimental robotics. With Kris, I am working on direct synthesis of robot controllers with model-based reinforcement learning where we do not need any past system knowledge. For an overview of my recent work, you can find a shortened version of my qualifying exam slides here, or a private recording here.

Novel Robotics: I want to be able to build useful robots from whatever pieces an engineer has.
Model-based Reinforcement Learning: I am optimistic about interpretable learning for robots.
Robot Learning in Weak-sensor Environments: As a practical roboticist (or a data-scientist), I want to make systems that work in all parts of the world.

Novel Robots

Reinforcement Learning

Multi-Agent Systems

Beneficial AI

Robotics

Model Learning

My CV Contact Google Scholar

Recent Papers

Paper pages have abstracts, videos, take-aways and more!

Novel Robots

Reinforcement Learning

AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks

Feb 4, 2021

Beneficial AI

McKane Andrus, Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, Tom Zick

IEEE International Symposium on Technology and Society

We study three developing subfields of AI research and their growing relationship with the sociotechnical: AI Safety, Fair Machine Learning, and Human-in-the-loop Autonomy.

Full Page

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Dec 21, 2020

Model Learning

Novel Robots

Reinforcement Learning

Nathan Lambert, Craig Schindler, Daniel S Drew, Kristofer SJ Pister

IEEE Robotics and Automation Letters

We explored how MBRL can learn multi-step, nonlinear controllers!

Full Page

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning

Dec 16, 2020

Model Learning

Robotics

Reinforcement Learning

Nathan O Lambert, Albert Wilcox, Howard Zhang, Kristofer SJ Pister, Roberto Calandra

Arxiv

Trying to reframe the MBRL framework with long-term predictions instead of one-step predictions!

Full Page

Learning for Microrobot Exploration: Model-based Locomotion, Robust Navigation, and Low-Power Deep Classification

Jul 13, 2020

Novel Robots

Robotics

Nathan Lambert, Fahran Toddywala, Brian Liao, Eric Zhu, Lydia Lee, Kristofer S.J. Pister

Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

A collections of steps towards a data-driven autonomous microrobot.

Full Page

Objective Mismatch in Model-based Reinforcement Learning

Feb 11, 2020

Model Learning

Reinforcement Learning

Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

2020 Conference on Learning for Decision and Control

Studying the numerical effects of a dual-optimization problem in model-based reinforcement learning -- control and dynamics. When optimizing model accuracy, there is no guarantee on improving task performance!

Full Page

Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning

Sep 26, 2019

Robotics

Reinforcement Learning

Tianyu Li,m, Nathan Lambert , Roberto Calandra , Franziska Meier , Akshara Rai

2020 IEEE International Conference on Robotics and Automation (ICRA)

Learning how to walk with a real-world hexapod using a hierarchy of model-free RL for basic motion primitives with model-based RL for higher level planning.

Full Page