Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
pxeger1
on Dec 8, 2023
|
parent
|
context
|
favorite
| on:
'A-team' of math proves a critical link between ad...
But AlphaGo etc don’t use any kind of language-based AI, so LLMs (which this thread was about) are no good.
thisismyswamp
on Dec 8, 2023
[–]
The next step seems to be applying past advances in reinforcement learning with modern transformer based models
mattsan
on Dec 8, 2023
|
parent
[–]
Which multiple teams are working on - OpenAI (Q*), and Meta just released a reinforcement learning framework
npsomaratna
on Dec 9, 2023
|
root
|
parent
[–]
Could you point me towards Meta's reinforcement learning framework? I'd like to see how it stacks up against the OpenAI gym.
mattsan
on Dec 10, 2023
|
root
|
parent
[–]
Sure thing -
https://pearlagent.github.io/
HN post here:
https://news.ycombinator.com/item?id=38564526
npsomaratna
on Dec 10, 2023
|
root
|
parent
[–]
Thank you!
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
