Questions tagged [go]

For questions related specifically for abstract strategy board game, go.

Filter by
Sorted by
Tagged with
6
votes
1answer
966 views

Is the new Alpha Go implementation using Generative Adversarial Networks?

I read through the publication Mastering the game of Go without Human Knowledge. It doesn't seem to use GANs, just a new form of search and reinforcement learning.
6
votes
4answers
1k views

Is the play of strong Chess AI easily distinguishable from human play?

I don't play nearly enough Chess to be able to answer. For context, AlphaGo is stronger than the current strongest human player, but AlphaGo's game play has been cast as "inhuman" in the sense that ...
6
votes
1answer
153 views

Are there human predictions of when a computer would have been better than a human at Go?

I just stumbled across the paper When Will AI Exceed Human Performance? Evidence from AI Experts, which contains a figure showing the aggregated subjective probability of "high-level machine ...
5
votes
1answer
120 views

Could AI kill the joy of competitive sports and games?

Lee Sedol, former world champion, and legendary Go player today announced his retirement with the quote "Even if I become the No. 1, there is an entity that cannot be defeated". Is it possible that ...
5
votes
1answer
878 views

How powerful is OpenAI's Gym and Universe in board games area?

I'm a big fan of computer board games and would like to make Python chess/go/shogi/mancala programs. Having heard of reinforcement learning, I decided to look at OpenAI Gym. But first of all, I would ...
5
votes
1answer
570 views

Can games be solved without an evaluation function?

Fundamentally, a game-playing AI must solve the problem of choosing the best action from a set of possible actions. Most existing game AI's, such as AlphaGo, do this by using an evaluation function, ...
3
votes
1answer
191 views

How Does AlphaGo Zero Implement Reinforcement Learning?

AlphaGo Zero (https://deepmind.com/blog/alphago-zero-learning-scratch/) has several key components that contribute to it's success: A Monte Carlo Tree Search Algorithm that allows it to better search ...
1
vote
1answer
292 views

Why was Go a harder game for an AI to master than Chess?

AI became superior to the best human players in chess around 20 years ago (when the 2nd Deep Blue match concluded). However, it took until 2016 for an AI to beat the Go world chess champion, and this ...
1
vote
1answer
945 views

How to design a good evaluation function for a go-like game?

I am trying to find a good evaluation function for a game with: A 7x7 tile board 2 players, given an equal number(>=3 currently undetermined) of stones placed randomly on the tiles A turn is ...
1
vote
0answers
20 views

Image-to-Image Regression for GO territory classification

I'm trying to implement a neural network that is able to generate an image indicating territory occupation given a board state for GO (a strategy board game). Input images are 19x19x1 grayscale images,...
0
votes
1answer
53 views

Were AI strategies identified at go or starcraft games and how?

When an AI is trained to play an opposing game, such as chess or go, it can become very strong. I have read in an article (non-scientific) the claim that AI strategies were identified by scientists ...
0
votes
0answers
38 views

Algorithm to evaluate Go board after turn

Can anyone help me with the algorithm used to evaluate the board once a player has played his turn in the game of Go? I have a vector representing the board, with a dimension for each postion . Player ...