Questions tagged [alphago-zero]

For questions related to AlphaGo Zero, which is a version of DeepMind's Go software, AlphaGo, that does not use data from human games and it is stronger than AlphaGo. There is a generalized version of AlphaGo Zero called AlphaZero, which beat the 3-day version of AlphaGo Zero by winning 60 games to 40. AlphaGo Zero was introduced in the paper "Mastering the game of Go without human knowledge" (2017) by David Silver et al.

Filter by
Sorted by
Tagged with
11 votes
1 answer
1k views

Why is the merged neural network of AlphaGo Zero more efficient than two separate neural networks?

AlphaGo Zero contains several improvements compared to its predecessors. Architectural details of Alpha Go Zero can be seen in this cheat sheet. One of those improvements is using a single neural ...
Demento's user avatar
  • 1,684
7 votes
3 answers
342 views

Would AlphaGo Zero become perfect with enough training time?

Would AlphaGo Zero become theoretically perfect with enough training time? If not, what would be the limiting factor? (By perfect, I mean it always wins the game if possible, even against another ...
Christopher King's user avatar
5 votes
1 answer
1k views

What is a "logit probability"?

DeepMind's paper "Mastering the game of Go without human knowledge" states in its "Methods" section on its "Neural network architecture" that the output layer of AlphaGo Zero's policy head is "A fully ...
sadakatsu's user avatar
  • 153
4 votes
1 answer
722 views

How does policy network learn in AlphaZero?

I'm currently trying to understand how AlphaZero works. There is one thing with the training of the AlphaZero's policy head that confuses me. Basically, in AlphaGo Zero's paper (where the major part ...
Alberto M's user avatar
3 votes
1 answer
235 views

AlphaGo Zero: does $Q(s_t, a)$ dominate $U(s_t, a)$ in difficult game states?

AlphaGo Zero AlphaGo Zero uses a Monte-Carlo Tree Search where the selection phase is governed by $\operatorname*{argmax}\limits_a\left( Q(s_t, a) + U(s_t, a) \right)$, where: the exploitation ...
user3667125's user avatar
  • 1,570
3 votes
1 answer
673 views

What is the input to AlphaGo's neural network?

I have been reading an article on AlphaGo and one sentence confused me a little bit, because I'm not sure what it exactly means. The article says: AlphaGo Zero only uses the black and white stones ...
user avatar
2 votes
3 answers
443 views

Does AlphaGo play random moves in a real competition?

Alphago and AlphaGo zero use random play to generate data and use the data to train DNN. "Random play" means that there is a positive probability for AlphaGo to play some suboptimal moves ...
High GPA's user avatar
  • 163