HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by zump | Hacker News Reader
Full thread
zump
·
Will RL take over Deep Convolutional Networks as having the best results?!
View on HN
qd6pwu4
·
I think they are parallel and can be used together, like Deep Reinforcement Learning.
nicklaf
·
I think they are parallel and can be used together
Yep:
https://en.wikipedia.org/wiki/AlphaGo#Algorithm
VodkaHaze
·
That's a sequential use. They got the initial strategy with DL, and made it stronger with MCTS
Reply on news.ycombinator.com