Democratizing Automation | Nathan Lambert | Substack

I make the case why people iteratively training any model should learn some core concerns of reinforcement learning.

New Top Community

Choices, risks, and reward reporting. Recommendations for how to integrate RL systems with society.

Feb 8

A tour of control theory, multi-agent RL, and hierarchical learning.

Jan 21

Industry labs power up their robot learning research with parallelization!

Aug 9, 2021

How RL is starting to be used by industry and how RL is heading to a framing more suited for industrial scales.

Aug 2, 2021

Multi-agent scenarios make reward maximization a risk. Discussing when, rather than if, we should believe in the Reward Hypothesis.

Jun 21, 2021

How simulator exploitation, a dual of over-optimization, in AI is the canary in the coal mine for what negative implications could come from…

Mar 19, 2021

I don’t even like the idea of flying delivery drones, but that will be all we have.

Feb 26, 2021

Social

Twitter Get in touch

Recommended

Mark Saroufim Breaking the Stagnation

Jack Clark Import AI

Democratizing Automation

About Archive Authors

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts