Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
energy123
38 days ago
|
parent
|
context
|
favorite
| on:
Q-learning is not yet scalable
DeepMind's earlier success with Atari was based on offline Q-Learning
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
