Open in app

Sign In

Write

Sign In

Nathan Lambert
Nathan Lambert

645 Followers

Home

About

Pinned

Navigating natolambert’s writing

You found me on Medium! I use their great search engine optimization to gather followers across a few modalities. — What I do: Robot learning research at UC Berkeley (PhD expected fall 2021). Write high-signal content on the internet on AI, robotics, and my interests (See below). Nerd out on training, longevity, and what it means to be alive. Support me financially with this link: https://natolambert.medium.com/membership

Writing

2 min read

Navigating natolambert’s writing
Navigating natolambert’s writing
Writing

2 min read


Published in Towards Data Science

·Nov 4, 2021

Boston Dynamics: Studying Athletic Intelligence

The acrobatic dance videos are flashy, but what are the actual technical breakthroughs? What is happening to the Korean robotics industry? — The robotics company that has a knack for viral technology videos showcasing little things robots can do, parkour, bullying robots, and more. A central tenet of Boston Dynamics is the idea of athletic intelligence — movement patterns that are robust, flexible, and maybe even human. These videos and technologies have…

Robotics

10 min read

Boston Dynamics: Studying Athletic Intelligence
Boston Dynamics: Studying Athletic Intelligence
Robotics

10 min read


Published in Towards Data Science

·Nov 2, 2021

Reward Maximization Is Not Enough for Complete Intelligence

Multi-agent scenarios make reward maximization a risk. Discussing when, rather than if, we should believe in the Reward Hypothesis. — Dopamine (below) is central to human experience. It is known to be involved in feeling a current pleasure — that is something you are experiencing and enjoying. Dopamine also plays a crucial role in predicting a future please — that is done in planning by releasing the same feeling of…

Machine Learning

10 min read

Reward maximization is not enough for complete intelligence
Reward maximization is not enough for complete intelligence
Machine Learning

10 min read


Published in Towards Data Science

·Oct 31, 2021

How all machine learning becomes reinforcement learning

I make the case why people iteratively training any model should learn some core concerns of reinforcement learning. — Thought exercise Consider these examples of an ML problem that has across-time effects on its models. This time-dependent function of reinforcement learning is where most of the “core pieces”(below) will emerge. Consider a system that is trying to reduce the churn (ended subscriptions) of a paid online membership. Such a company could…

Machine Learning

12 min read

How all machine learning becomes reinforcement learning
How all machine learning becomes reinforcement learning
Machine Learning

12 min read


Published in Towards Data Science

·Apr 6, 2021

Debugging Deep Model-based Reinforcement Learning Systems

Lessons learned from a PhD in a young field. — I saw an example of this debugging lessons for model-free RL and felt fairly obliged to repeat it for MBRL. Ultimately MBRL is so much younger and less pervasive, so if I want it to keep growing I need to invest that time in all of you. For an illustrative…

Reinforcement Learning

17 min read

Debugging Deep Model-based Reinforcement Learning Systems
Debugging Deep Model-based Reinforcement Learning Systems
Reinforcement Learning

17 min read


Published in Towards Data Science

·Jan 22, 2021

Robotic Companies 2.0: Horizontal Modularity

How behaving as a digital platform rather than a manufacturer will be the sweet spot for the next generation of robotics companies — Data and deep learning have been changing the world for the last decade. Most robotics companies have not tapped into the datavolution and the mainstream vision for what robotics can be is still far from realized. …

Robotics

7 min read

Robotic Companies 2.0: Horizontal Modularity
Robotic Companies 2.0: Horizontal Modularity
Robotics

7 min read


Published in Towards Data Science

·Jan 9, 2021

The Ubiquity and Future of Model-based Reinforcement Learning

Where a hot new research sub-field is going in RL. — As many of you know, I am doing my PhD centered around model-based reinforcement learning (MBRL). This post is not talking about the technical details and recent work, but rather why I am bullish on it for the future. Beyond the prospects of how well it can perform (it’s much…

Reinforcement Learning

8 min read

The Ubiquity and Future of Model-based Reinforcement Learning
The Ubiquity and Future of Model-based Reinforcement Learning
Reinforcement Learning

8 min read


Published in Towards Data Science

·Jan 9, 2021

Free Will & Artificial General Intelligence (AGI)

Lessons about AI from lessons about our mind. Focused on the nature of free will. — I have been trying to train my mind through meditation for about two years now. It is remarkable to me the frequency and ease by which you can notice the actual modus operandi of the brain differing from the perceived modus operandi. …

Machine Learning

11 min read

Free Will & Artificial General Intelligence (AGI)
Free Will & Artificial General Intelligence (AGI)
Machine Learning

11 min read


Published in Towards Data Science

·Dec 15, 2020

Robotics and Deep Reinforcement Learning at Neural Information Processing Systems (NeurIPS) 2020

I tried my best to absorb a lot of content at NeurIPs 2020, and it was just as overwhelming as ever. Everyone makes decisions of what content they want to focus on, and it is always an exploration (learn new things) versus exploitation (further mastering material in your area of…

Machine Learning

11 min read

Robotics and Deep Reinforcement Learning at Neural Information Processing Systems (NeurIPS) 2020
Robotics and Deep Reinforcement Learning at Neural Information Processing Systems (NeurIPS) 2020
Machine Learning

11 min read


Published in Towards Data Science

·Nov 8, 2020

Constructing Axes for Reinforcement Learning Policy

A small step into the research community’s most opaque framework. — Reinforcement learning (RL) — the framework of interacting with an environment to learn a policy to act and achieve some objective — is on the up in many domains. Some domains make sense, some will never work, and most are bound to fall somewhere in the middle. RL is so…

Reinforcement Learning

8 min read

Constructing Axes for Reinforcement Learning Policy
Constructing Axes for Reinforcement Learning Policy
Reinforcement Learning

8 min read

Nathan Lambert

Nathan Lambert

645 Followers

Trying to think freely and create equitable & impactful automation @ UCBerkeley EECS. Subscribe directly at robotic.substack.com. More at natolambert.com

Following
  • Cornell University

    Cornell University

  • Vincent Vanhoucke

    Vincent Vanhoucke

  • Clément Delangue

    Clément Delangue

  • Lex Fridman

    Lex Fridman

  • Victor Lambert

    Victor Lambert

See all (5)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech