Skip to main content
15 votes
Accepted

How does "Monte-Carlo search" work?

Monte Carlo method is an approach where you generate a large number of random values or simulations and form some sort of conlusions based on the general patterns, such as the means and variances. As ...
Disenchanted Lurker's user avatar
14 votes
Accepted

Is AlphaZero an example of an AGI?

Good question! AlphaZero, though a major milestone, is most definitely not an AGI :) AlphaGo, though strong at the game of Go, is narrowly strong ("strong-narrow AI"), defined as strength in a ...
DukeZhou's user avatar
  • 6,237
10 votes
Accepted

Is the new AlphaGo implementation using Generative Adversarial Networks?

No, GANs are not used. It's reinforcement learning at what it does best. The tree search is an interesting addition and assists with navigating the sheer scale of the game. Although the agent was ...
Jaden Travnik's user avatar
9 votes
Accepted

Does the recent advent of a Go playing computer represent Artificial Intelligence?

There are at least two questions in your question: What are some of the methods used to program the successful go playing program? and Are those methods considered to be artificial ...
miku's user avatar
  • 860
7 votes

Did Alphago zero actually beat Alphago 100 games to 0?

Did AlphaGo and AlphaGo [Zero] play 100 repetitions of the same sequence of boards, or were there 100 different games? There were 100 different games. You can view some example games between AlphaGo [...
Neil Slater's user avatar
  • 32.7k
6 votes

Does the recent advent of a Go playing computer represent Artificial Intelligence?

It doesn't make much sense to have a single threshold with "unintelligent" below it and "intelligent" above it. I think it makes more sense to have a gradation of intelligence by cognitive task. ...
Matthew Gray's user avatar
  • 4,272
6 votes
Accepted

Why did AlphaGo lose its Go game?

We know what Lee's strategy was during the game, and it seems like the sort of thing that should work. Here's an article explaining it. Short version: yes, we know what went wrong, but probably not ...
Matthew Gray's user avatar
  • 4,272
6 votes
Accepted

Why is chess still a benchmark for Artificial Intelligence?

Chess isn't really a benchmark per say. The method developed in AlphaGo to play Go should in principle generalize quite nicely to other games of this sort, such as chess. Since Stockfish is quite ...
k.c. sayz 'k.c sayz''s user avatar
6 votes

Why didn't champion of the Go game manage to win the last game against AlphaGo, after winning the 4th one?

The technique used by AlphaGo is "Monte Carlo Tree Search", combined with a very well trained neural network. The network's job is to estimate the quality of different board states and moves. This ...
John Doucette's user avatar
4 votes
Accepted

What part of the game is the value network trained to predict a winner on?

To my understanding, this is basically a supervised learning problem, where from the self play we have games associated with their winners, and the network is being trained to map game states to ...
Neil Slater's user avatar
  • 32.7k
4 votes

Would AlphaGo Zero become perfect with enough training time?

Assuming you mean a mathematically perfect player, similar to what we can achieve trivially in Tic Tac Toe, then the answer is "maybe". The underlying reinforcement learning algorithms that it uses do ...
Neil Slater's user avatar
  • 32.7k
4 votes

Would AlphaZero perform better if made with transformers?

Yes! LeelaChessZero, an open-source re-implementation and continuation of AlphaZero, has been experimenting with this for a while now. Their strongest networks are currently transformers, not ...
KarelPeeters's user avatar
3 votes

Does the recent advent of a Go playing computer represent Artificial Intelligence?

Now that this milestone has been reached, does that represent a significant advance in artificial intelligence techniques or was it just a matter of ever more processing power being applied to the ...
wythagoras's user avatar
  • 1,521
3 votes

Why is a constant plane of ones added into the input features of AlphaGo?

I wonder why these features are necessary, because I think a constant plane contains no information and it makes the the network larger and consequently harder to train. In many implementations of ...
Dennis Soemers's user avatar
  • 10.4k
3 votes
Accepted

Would AlphaGo Zero become perfect with enough training time?

We cannot tell with certainty whether AlphaGo Zero would become perfect with enough training time. This is because none of the parts (Neural Network) that would benefit from infinite training time (= ...
Dennis Soemers's user avatar
  • 10.4k
3 votes

Would it take 1700 years to run AlphaGo Zero in commodity hardware?

Although the above statement holds important analogies to communicate the technical advances made by deep mind in the development of Alpha Go. It is inaccurate and should be taken skeptically. ...
Seth Simba's user avatar
  • 1,186
2 votes

Does the recent advent of a Go playing computer represent Artificial Intelligence?

We've had many discussions on what constitutes Artificial Intelligence, and my takeaway has been that decision-making is the core requirement of AI, regardless of the optimality of that decision. ...
DukeZhou's user avatar
  • 6,237
2 votes

Would AlphaGo Zero become perfect with enough training time?

Yes AlphaGo Zero could become undeniably perfect. It has won 100:0 against AlphaGo Lee (which won 4:1 against 18-time world champion (human) Lee Sedol) and 89:11 against AlphaGo Master (which won 60 ...
Rob's user avatar
  • 632
2 votes

Is it fair to compare AlphaGo with a Human player?

Is it fair to compare AlphaGo with a Human player? Depends on the purpose of the comparison. If we are comparing ability to win a game of Go, then yes. If we are comparing learning ability, then ...
Neil Slater's user avatar
  • 32.7k
2 votes
Accepted

Alphazero policy head loss not decreasing

The loss of the policy head here is really quite different from losses in, for instance, more "conventional" Supervised Learning approaches (where we typically expect/hope to see a relatively steady ...
Dennis Soemers's user avatar
  • 10.4k
2 votes

Why is Monte Carlo used as the tree search algorithm for AlphaGo?

The paper that introduced AlphaGo, Mastering the game of Go with deep neural networks and tree search, motivates the use of MCTS Monte Carlo tree search (MCTS) uses Monte Carlo rollouts to estimate ...
nbro's user avatar
  • 41k
2 votes

Is which sense was AlphaGo "just given a rule book"?

it was "just given the rulebook", what does this mean? Literally a book written in English to read? The program was not given a natural language version of the rules to interpret. That ...
Neil Slater's user avatar
  • 32.7k
2 votes

Does AlphaGo play random moves in a real competition?

Question 1: I don't think they ran AlphaGo or AlphaGoZero in training mode during tournament matches because the computing power required for this is really large. I don't recall if this is described ...
Lars's user avatar
  • 189
2 votes
Accepted

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

I don't think you've necessarily made any real mistakes in your calculations or anything like that, that all seems accurate. I can't really confidently answer your questions about "Does X usually ...
Dennis Soemers's user avatar
  • 10.4k
1 vote
Accepted

Initialising DQN with weights from imitation learning rather than policy gradient network

My understanding is that you are first training a policy network using imitation learning. Then you are adjusting that trained network in some way to be a value network for DQN. The most obvious ...
Neil Slater's user avatar
  • 32.7k
1 vote

Is it possible for AlphaGo Zero to use recurrent networks to achieve similar performance?

I can't think of any reason why using an RNN wouldn't work in theory. In practice RNNs are slightly harder to train (they can be unstable, and ever more practically you have to deal with multiple ...
KarelPeeters's user avatar
1 vote

Does AlphaGo play random moves in a real competition?

AlphaGo/AlphaZero has 3 main sources of randomness during competitive mode: Move temperature: The MCTS process outputs a probability distribution P over all candidate moves. The agent chooses a move ...
dshin's user avatar
  • 161
1 vote

Does AlphaGo play random moves in a real competition?

The core mechanics of AlphaZero during selfplay and real tournament games are the same: something similar to Monte Carlo Tree Search is done but guided by the current neural network instead of random ...
KarelPeeters's user avatar
1 vote

What is the search depth of AlphaGo and AlphaGo Zero?

For easier visualization, I recommend this video: https://twitter.com/i/status/1257053365424578565 The more detailed article about GO algorithms: https://deepmind.com/blog/article/alphago-zero-...
Piotr Żak's user avatar
1 vote
Accepted

How does the AlphaGo Zero policy decide what move to execute?

The formula in question uses a function N(state, action) that defines a visit count of a state-action pair (introduced on page 3). To describe how it is used, lets first describe the steps of AlphaGo ...
Jaden Travnik's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible