Hot answers tagged

14

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 an example, you could use it for weather forecasts. Predicting long-term weather is quite difficult, because it is a chaotic system where small changes can ...


8

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 intelligence (in that it does actually give better outcomes as more effort is expended) but very, very low intelligence (as the outcomes are better mostly by luck, ...


7

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 determine an action based in a tree representation. The differences among all these version are their exploration and exploitation mechanisms, and it is necessary to ...


7

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 decisions based on what's happened before in similar instances. For something to be intelligent, it needs a way to keep track of what it's learned. A chess ...


5

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 part because there's more academic interest in developing strategies for those games. The basic structure of a game-playing AI is that it takes in game state ...


5

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 networks. These are not the whole of AI by any means, expecially in a historical context, but they have recently been very successful, there is lots of published ...


4

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 (basically would have to know every single tiny detail of your implementation to be able to reproduce). Some things to consider: The size of your transposition table ...


4

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 reduction. At present, there are few definite rules for doing this: practice is more a question of 'informed trial and error'. If you add some information to ...


3

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-Limit (HUNL) Poker) which is freaking many professional poker players out. In the DeepStack arxiv paper, they say AI techniques (Cepheus) have previously ...


3

One simple approach to consider would be storing each statement as a template made in advance. Will there be less/more than x goals scored in the match? Will player score a goal during the match? ... The system will pick a random statement and will fill the variable fields with some statistically generated data between teamA and teamB; here you have your ...


3

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 by the joystick controller Regarding VGDL, as far as I can see, the main site associated with it is gvgai.net, which is currently down. The associated API is ...


3

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 the result is bad, all the actions in the game are suppressed. This sounds weird because in each game regardless of the end result you'll have many good and bad ...


2

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. Since the first goal in AI is to find any solution, nothing can beat the brute force approach. But then using the previous results of brute force approaches, the ...


2

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 if statements. This is an AI no matter how poorly coded/designed it is. The chess playing computer beating a human professional can be seen as a meaningful ...


2

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 recent breakthrough where (deep)neural nets with deep search techniques like monte-carlo search, etc; which might be more human-like and demonstrate a much ...


2

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 that the MCTS algorithm will not get to the "big win" move because it will be selecting more promising moves further up the tree. Some things to think about (read ...


2

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 decisions, and the best way to do this is the approach taken to teaching an AI to play Go - seeing thousands of example games by experts, and playing itself thousands ...


2

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 rules from human played chess games. Once the rules are known, we could use reinforcement learning to improve playing strength (and other board games).


1

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 Difference loss function was that it was essentially training on itself, that is data produced by the same method was used as part of regression target. That was ...


1

My understanding - from comments on the question - is that you are looking to train a Reinforcement Learning agent on the game of Tic Tac Toe (perhaps just in theory), where the agent should learn to play against a "human" opponent. In practice you may want a model of a human opponent. In this case, the RL agent will be presented with a board state, it will ...


1

Investigating reinforcement as a way of producing more interesting behavior than behavior trees for AI based commercial strategy game development is a good idea. The simple test game given can be described briefly. Human pitted against AI Each player gets a fleet of ships Each ship begins with a positive health level One ship can be ordered to fire one shot ...


1

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 Further information and piece of code to implement it can be found in SO here Hope it helps !


1

I changed the layer from tf.contrib.rnn.LSTMBlockCell to tf.contrib.rnn.LayerNormBasicLSTMCell. Then the gradients become large enough to influence the network.


1

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/games_research.html Here's Laird's overview article from 'Computer': https://www.researchgate.net/profile/John_Laird/publication/...


1

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-the-surface-of-a-sphere-with-tiles-how-might-you-deal-with-polar-d and https://gamedev.stackexchange.com/questions/45167/square-game-map-rendered-as-sphere for ...


1

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 ) tied to the users position ( which is known ), so there is nothing really intelligent in the strict sense, it just looks that way. In your case I would look into ...


1

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 ingredients for this are: A list of all the actions that a snake can immediately perform from its current position. A measure of quality (a.k.a. 'fitness') ...


1

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 scientific environments where the system is "trained" on a huge data set to adjust the "weights" (variables) for a given problem. This "training" process requires ...


1

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 hits local optima, because its not exhaustive.


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