A message from our CEO about the future of Stack Overflow and Stack Exchange. Read now.
8

Alexander Kronrod once said, “Chess is the Drosophila of artificial intelligence”. John McCarthy disagrees with this statement. I think it's primarily because he has different vision.Techniques and Innovative methods developed to play these games have been found useful over the wide spectrum of Computer Science (and not just Artificial Intelligence). The ...


7

The allegation was based on the fact that Deep Blue made a choice that did not yield the immediate (or short term) benefit that was synonymous with systems back then (1997). Computational capability was significantly less powerful then, and Kasparov claimed that only a grand master would have made the decision that the system did - so the deep blue team ...


7

Not all games (or even board games) are computationally algorithmic. Even the least skilled player is likely to trounce the hottest pattern-matching algorithm in a game of Pictionary (for example). If you want to say that the movement of pieces upon successful completion of a task is only ancelary to the object of the game, than your answer will be largely ...


7

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 intelligence? The first question is deep and technical, the second broad and philosophical. The methods have been described in: Mastering the Game of Go with Deep Neural ...


6

I would like to use reinforcement learning to make the engine improve by playing against itself. I have been reading about the topic but I am still quite confused. Be warned: Reinforcement learning is a large complex subject. Although it might take you on a detour from game-playing bots, you may want to study RL basics. A good place to start is Sutton &...


6

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. Inverting a matrix is a 'cognitive task,' and one where working memory pays off immensely; computers have been much better at that cognitive task than humans for a ...


6

This relates to the concept of "solved games". In general, two player turn-based games with perfect information - of which chess is an example - can result in all three possible outcomes: a forced win for white, a forced win for black, or a forced draw. The short, although unsatisfactory answer is that chess is not solved, and it is not clear whether it can ...


5

For many years, the focus has been on games with perfect information. That is, in Chess and Go both of us are looking at the same board. In something like Poker, you have information that I don't have and I have information that you don't have, and so for either of us to make sense of each other's actions we need to model what hidden information the other ...


5

Instead of having the AI learn what action to take, you can alternatively train it to judge how "good" a position is. In order to determine what move to make, you don't ask the AI "This is the current state, what move should I make", you iterate through all possible moves, and feed the the resulting state into the AI asking "How good do you think this new ...


5

As I see it, it all comes down to game theory, which can be said to form the foundation of successful decision making, and is particularly useful in a context, such as computing, where all parameters can be defined. (Where it runs into trouble is with the aggregate complexity of the parameters per the "combinatorial explosion", although Machine Learning has ...


4

This may be an evolving answer, because the question is, in some sense, a (useful) rabbit hole. I apologize if I don't go deeply into meta-games per se, as it's a little outside of my scope, which is non-chance games of perfect information, but I think it's worthwhile to think about the underlying problem of indeterminacy in relation to games in general. ...


4

Filling values is totally fine. In the case of image recognition the filling will be the background of the image (examples). For example in Belot you have total of 32 cards, which can be 32 boolean features. You can set the ones the player has to 1, while the rest are 0. Note that the in most games you'll need more features than the cards in your hand. I.e ...


4

These are big areas, so here is a brief description of the differences: Game theory is concerned with studying solutions for 'games', which are basically a set of decisions leading to certain outcomes. In game theory you look at strategies to achieve the best outcome for a given participant. One classic example (which isn't really a game in the traditional ...


3

This question is re-inventing the analysis for iterated prisoner's dilemma and the co-evolution that can lead to agents playing super-rationally in the one-shot version, which has been studied really extensively. Dan Ashlock's research career looked at this in great detail from an evolutionary perspective, but it's also been widely studied in other areas ...


3

Why is Game Playing R&D a Focus of Resource Allocation? When examining the apparent obsession with game playing as researchers attempt to simulate portions of human problem solving abilities, the orthodoxy of the views of John McCarthy (1927 – 2011) may be misleading. Publication editorial bias and popular science fiction themes may obscure the ...


3

Considering your use case, I would not use Deep Learning methods... what is the point? Instead of just winning, good AI is fun to play with. In practice when fine tuning game mechanics, you will want to analyze the game for churning events. Then it would be nice, if you could show the AI that "Hey, this is messed up, could you come up with a nice way of ...


3

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 problem? Neither, really. It is a milestone and a significant advance in computers beating humans in games, but the techniques used are only relevant to that game,...


3

If the game is not sequential, there would be no game tree and no need for pruning. Alpha-beta is a technique applied to look-ahead search. Alpha-beta has demonstrated utility in algorithms that play combinatorial games. (Even in iterated dilemmas, it doesn't really branch because it's simultaneous, more of a vine than a tree. Decisionmaking would be ...


3

Catan is actually a much more complicated game than the simple rules would suggest, and an exact solution is probably beyond the scope of current AI techniques. Monte Carlo Tree Search or Expectiminimax techniques seem like they could help, but are intended for games of perfect information. Catan is not a game of perfect information (the development cards ...


2

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. In this conception, Nimatron (1939, US2215544A) might be thought of as the first proper AI, pending verification of a a fabled Babbage Tic-Tac-Toe machine. ...


2

This second answer attempts to address perfect play in relation to incomplete information specifically. An element in the difficulty in answering this question may be that the concept of perfect play is widely applied to solved games in the domain of Combinatorial Game Theory as opposed to strictly economic Game Theory. In relation to games with incomplete ...


2

I find the statement troubling as the first confirmed algorithmic intelligence may have been a NIM automata, so from my perspective, the development of Algorithmic Intelligence is inseparable from combinatorial games. it would also seem that McCarthy does not hold the opinion that games are useful, which leads me to suspect he has never seriously studied the ...


2

I think you're going to have to be reconciled to the subjective nature of reality. Objectivity is only possible in very special cases such as a Q.E.D. in mathematics, or a solved gamed. Rationality is bounded, and any intractable problem results in a state of subjectivity/indeterminacy. Additionally, pure values do not carry moral implications, despite ...


2

Minimax deals with two kinds of values: Estimated values determined by a heuristic function. Actual values determined by a terminal state. Commonly, we use the following denotational semantics for values: A range of values centered around 0 denote estimated values (e.g. -999 to 999). A value less than the smallest heuristic value denotes a loss for max (e....


2

Isn't the events of world by the analysis of them with logic only result in an outcome of that analysis if those events were determined in the first place by logic. Not every event in the world is a consequence of logic and is not also a consequence of an illogical action either. The consequence of events as a result of the application logic results in ...


2

It's currently just too complex The different sources of information are too varied, in economics this is often referred to as a local knowledge problem, which hampers many large scale plans. Humans can react to slight differences like respecting local traditions, landscapes, history but an artificial intelligence would (currently at least) struggle not to ...


2

Historically, the non-ML approach would be an expert system. This is typically a rules-based decision system, falling under the umbrella of symbolic AI. These systems can have strong utility in limited contexts, but are generally "brittle" in that parameters not previously defined or accounted will produce no-compute or weak utility. Because the rules of ...


2

There are multi-objective optimization problems, where the objective functions may be in conflict with each other, which can potentially have multiple Pareto-optimal solutions. The paper Multi-objective optimization using genetic algorithms: A tutorial (2006) gives a good overview of the multi-objective optimization problem with genetic algorithms, which can ...


2

MOEAs sounds very cool, but I feel that you can't really talk about conflict in AI without discussing generative adversarial networks (GANs), which have been shown to have amazing performance by training a model to say detect in-between pictures of cats and dogs and an adversarial network being trained to create pictures to attempt to trick the training ...


1

Yes, a baby can be considered an AI. Will this be our future? I don't know. That is exactly what some people are looking for, to create an AI that can live. We have several AIs that each time more surprises us. But none of them question their own existence, none of them wants to know or require attention from their god (developer) because of their ...


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