Democratizing Automation
Subscribe
Sign in
Home
Archive
About
New
Top
Discussion
Designing Societally Beneficial Reinforcement Learning Systems
Choices, risks, and reward reporting. Recommendations for how to integrate RL systems with society.
Nathan Lambert
Feb 8
2
Share this post
Designing Societally Beneficial Reinforcement Learning Systems
robotic.substack.com
Copy link
Twitter
Facebook
Email
Flexible Centralization in Multi-agent Learning & Control
A tour of control theory, multi-agent RL, and hierarchical learning.
Nathan Lambert
Jan 21
3
Share this post
Flexible Centralization in Multi-agent Learning & Control
robotic.substack.com
Copy link
Twitter
Facebook
Email
Remote robotic-data farms
Industry labs power up their robot learning research with parallelization!
Nathan Lambert
Aug 9, 2021
3
Share this post
Remote robotic-data farms
robotic.substack.com
Copy link
Twitter
Facebook
Email
on the Horizon of applied RL
How RL is starting to be used by industry and how RL is heading to a framing more suited for industrial scales.
Nathan Lambert
Aug 2, 2021
4
Share this post
on the Horizon of applied RL
robotic.substack.com
Copy link
Twitter
Facebook
Email
Reward is not enough
Multi-agent scenarios make reward maximization a risk. Discussing when, rather than if, we should believe in the Reward Hypothesis.
Nathan Lambert
Jun 21, 2021
2
Share this post
Reward is not enough
robotic.substack.com
Copy link
Twitter
Facebook
Email
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.
Nathan Lambert
Jun 14, 2021
7
Share this post
How all machine learning becomes reinforcement learning
robotic.substack.com
Copy link
Twitter
Facebook
Email
Setting ourselves up for exploitation: RL in the wild
How simulator exploitation, a dual of over-optimization, in AI is the canary in the coal mine for what negative implications could come fromā¦
Nathan Lambert
Mar 19, 2021
4
1
Share this post
Setting ourselves up for exploitation: RL in the wild
robotic.substack.com
Copy link
Twitter
Facebook
Email
Counting down until consumer drones are banned in cities
I donāt even like the idea of flying delivery drones, but that will be all we have.
Nathan Lambert
Feb 26, 2021
3
1
Share this post
Counting down until consumer drones are banned in cities
robotic.substack.com
Copy link
Twitter
Facebook
Email
Clarifying RL: Obscure problem formulations and structure tradeoffs
Some debates that will be settled en route to RL being used in all corners of the modern world.
Nathan Lambert
Feb 19, 2021
2
2
Share this post
Clarifying RL: Obscure problem formulations and structure tradeoffs
robotic.substack.com
Copy link
Twitter
Facebook
Email
Decoupling AI from the latent variable of spoken languages
How English being the language of progress in AI could bias our machineās minds and what we think they are capable of. Uncoupling AI from our notion ofā¦
Nathan Lambert
Feb 12, 2021
2
Share this post
Decoupling AI from the latent variable of spoken languages
robotic.substack.com
Copy link
Twitter
Facebook
Email
100th anniversary of the word robot: COVID didnāt give us personal robots, it gave us Woebot
Yes COVID accelerated automated manufacturing and logistics, but robots have not been helping out en masse anywhere else.
Nathan Lambert
Feb 5, 2021
1
Share this post
100th anniversary of the word robot: COVID didnāt give us personal robots, it gave us Woebot
robotic.substack.com
Copy link
Twitter
Facebook
Email
Boston Dynamics š¤š: Studying Athletic IntelligenceĀ
The acrobatic dance videos are flashy, but what are the actual technical breakthroughs? What is happening to the Korean robotics industry?
Nathan Lambert
Jan 29, 2021
4
Share this post
Boston Dynamics š¤š: Studying Athletic IntelligenceĀ
robotic.substack.com
Copy link
Twitter
Facebook
Email
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts