Hot answers tagged

8 votes

Are methods of exhaustive search considered to be AI?

If one thinks of intelligence as a continuous measure of optimization power (that is, how much better are outcomes for any unit of cognitive effort expended), then exhaustive search has non-zero ...
user avatar
7 votes

Are methods of exhaustive search considered to be AI?

If a computer is just brute-forcing the solution, it's not learning anything or using any kind of intelligence at all, and therefore it shouldn't be called "artificial intelligence." It has to make ...
user avatar
  • 2,559
7 votes
Accepted

How do I know when to use which Monte Carlo method?

They are all called Monte Carlo because all of them are a different version of the canonical Monte Carlo algorithm. The canonical version of Monte Carlo algorithm is a stochastic algorithm to ...
user avatar
5 votes
Accepted

How does artificial intelligence work in games?

There are many different kinds of AI used in games; AI for historical board games (like chess or Go) tends to be much better than AI for computer games (such as Starcraft or Civilization), in large ...
user avatar
5 votes
Accepted

How is the AI in 3d games implemented?

Overlap between AI and "Game AI" Nowadays, if you search for AI online, you will find a lot of material about machine learning, natural language processing, intelligent agents and neural ...
user avatar
  • 23.1k
4 votes
Accepted

Transposition table is only used for roughly 17% of the nodes - is this expected?

I don't think that's necessarily a strange number. It's impossible for anyone to really tell you whether that 17% is "correct" or not without reproducing it, which would require much more info (...
user avatar
  • 9,316
4 votes
Accepted

How to separate image recognition from logic?

The underlying abstraction (which is essentially what you'd be using the first network for) is that of reducing the state-space of the raw input via feature extraction/synthesis and/or dimensionality ...
user avatar
3 votes
Accepted

What's stopping Cepheus from generalizing to full poker games?

The reason why Cepheus can't generalize has to do with the number of decision points. The same authors recently let loose Deep Stack (DeepStack: Expert-Level Artificial Intelligence in Heads-Up No-...
user avatar
3 votes

How does deepmind's Atari game AI work?

Training happens once you have a result. If the result is good (maybe you won in pong, or you improved your highscore in breakout) all the actions in the game are "supported" by backpropagation, if ...
user avatar
3 votes

Could AI be used to generate questions from a database input?

One simple approach to consider would be storing each statement as a template made in advance. Will there be less/more than x ...
user avatar
  • 322
3 votes
Accepted

What are the benefits of the VGDL over the ALE?

Here is a description of the input to an ALE agent: Percept state: A single game screen (frame): a 2D array of 7-bit pixels, 160 pixels wide by 210 pixels high. Actions: 18 discrete actions defined ...
user avatar
2 votes

Are methods of exhaustive search considered to be AI?

Brute force approach is certainly the first step of many in AI programming. But using these experiences the program must learn to find the best solution or at least a closer solution to the problem. ...
user avatar
  • 51
2 votes

Are methods of exhaustive search considered to be AI?

Really any 'intelligence' exhibited by a computer is deemed AI, regardless of brute force or use of smart heuristics. For example, a chat bot can be coded to respond to most responses using many, many ...
user avatar
  • 749
2 votes

How does artificial intelligence work in games?

Most of the existing AI bots which can play games use deep search from possible space and choose the best move. This is done by most of the chess, Go, Tic-Tac-Toe, etc bots. However, there has been a ...
user avatar
  • 1,341
2 votes
Accepted

How close are we to having an AI that can play Magic: The Gathering objectively well?

This is a very specific task, with clearly defined parameters, so it would already theoretically be within the scope of current AI technology to do this. The AI would need to learn how to make ...
user avatar
2 votes

Monte Carlo Tree Search: What kind of moves can easily be found and what kinds make trouble?

Whether the move is found and how quick it is found depends on a few things. If I understand correctly, there is a sequence of many "bad" moves which lead to the "big win" move, and you are afraid ...
user avatar
2 votes

Can an AI learn how to play chess without instructions?

It's possible for an AI to learn chess without even knowing how to move the pieces. Google's AlphaZero didn't do that as their programmers coded the chess rules, but it's possible. One can learn the ...
user avatar
  • 1,368
1 vote

How do the achievements met in the gaming field (ex. AlphaGo Zero) impact other fields of application?

Yes it's created something important. Until Alpha(Go) Zero all (or almost all) of Deep Learning approach to Reinforcement Learning was based on Time Difference loss function. The weakness of Time ...
user avatar
1 vote

Too small gradient on large neural network

Vanishing gradient is a common problem in RNN. A common way to deal with it is the method of gradient clipping (mainly you define a maximum and/ or a minimum threshold). see here for more information ...
user avatar
  • 113
1 vote

Too small gradient on large neural network

I changed the layer from tf.contrib.rnn.LSTMBlockCell to tf.contrib.rnn.LayerNormBasicLSTMCell. Then the gradients become large enough to influence the network.
user avatar
  • 29
1 vote

Different useful approaches of implementing real-time AI?

About 15 years ago, John Laird's group at Michigan used the Soar rule-based architecture to play several FPS games effectively (Quake II, Descent III): http://ai.eecs.umich.edu/people/laird/...
user avatar
  • 671
1 vote

How to create an AI snake for a video game?

Divide the globe into a "cells". Each cell will have a number of neighbours depending on how you have divided your globe. Have a look at https://gamedev.stackexchange.com/questions/3360/when-mapping-...
user avatar
1 vote

How to create an AI snake for a video game?

In general, AI in this type of video games is mostly pathfinding (giving the program a map of possible object positions) and/or an algorithm or series of algorithms ( so it looks random or alive ) ...
user avatar
  • 575
1 vote

How to create an AI snake for a video game?

A relatively simple option which uses AI techniques that are 'traditional' for adversarial games (and which is therefore less of a 'research project' than the use of Machine Learning) is Minimax. The ...
user avatar
1 vote

What sort of game problems can neural networks trained/evolved with evolutionary algorithms solve, and how are they typically implemented?

Without going in too much detail on how exactly Neural Networks and Generic Algorithms work, I can tell you that both the algorithms are not good candidates for computer games. They work well in ...
user avatar
1 vote

Are methods of exhaustive search considered to be AI?

I dont know why you wouldnt consider it ai since every single thing has used something like it thats been in the recent news. evolving a neural network is very similar to brute force search, just it ...
user avatar
  • 11

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