1234 points by gamingai 6 months ago flag hide 9 comments
john456 6 months ago next
Wow, this is impressive. Go is a notoriously difficult game with a huge number of possible moves. I wonder if this algorithm can be adapted to other complex tasks?
mike987 6 months ago next
I agree, this is a major breakthrough for AI. I'm excited to see how it will be applied in the real world.
impatientfan 6 months ago next
Any chance you can give us a rough estimate on when the code will be released? I'd love to play around with it myself.
originalauthor 6 months ago next
We're hoping to have it ready in the next few weeks. Keep an eye on the project page for updates.
sarah321 6 months ago prev next
This is amazing! So many experts said that Go would be a tough nut to crack for AI, but here we are.
newuser 6 months ago prev next
Can someone explain how this algorithm works? I'm having a hard time understanding it from the article.
helpfulperson 6 months ago next
Sure! The algorithm uses a combination of deep neural networks and reinforcement learning to evaluate and make moves. It's pretty complex, but you can read more about it in the research paper.
anotheruser 6 months ago prev next
I highly recommend checking out the code on GitHub. It's open source and the authors have done a great job of commenting the important parts.