22
votes
Are humans superior to machines in chess?
Losing games to computers because of mistakes made under time pressure was probably a thing about 20 years ago, when Kasparov lost to DeepBlue after such a mistake(correction: it was Kramnik with the ...
- 890
20
votes
How do neural networks play chess?
Minimax and related algorithms are used to play chess. That is how chess programs have worked for many years (with some additions such as standard opening playbooks). They do not need to process the ...
- 30.3k
17
votes
Accepted
Why were Chess experts surprised by the AlphaZero's victory against Stockfish?
Good question.
First and foremost is that in Go deepmind had no superhuman opponents to challenge. Go engines were not anywhere near the highest level of the top human players. In chess, however, ...
- 186
12
votes
How do neural networks play chess?
This is a good question. your understanding in general is correct. Indeed, data can be used to construct a proper evaluation of a move/board position and recommended moves based on its history (at ...
- 823
11
votes
Accepted
Why spend so much time and money to build AIs to play games?
In the book Artificial Intelligence: A Modern Approach (section 5.7, p. 185), Russell and Norvig write
In 1965, the Russian mathematician Alexander Kronrod called chess "the Drosophila of ...
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 ...
- 4,262
7
votes
Accepted
How could Deep Blue possibly cheat?
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 ...
- 716
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 ...
- 2,589
7
votes
If two perfect chess AI's played each other, would it always be a stalemate or would white win for an inherent first-move advantage?
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 ...
- 30.3k
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 ...
- 2,071
6
votes
What is the definition of rationality?
When we use the term rationality in AI, it tends to conform to the game theory/decision theory definition of rational agent.
In a solved or tractable game, an agent can have perfect rationality. If ...
- 6,237
6
votes
Accepted
Clarifying representation of Neural Nerwork input for Chess Alpha Zero
For anyone wondering, I believe to have found the answer:
Yes, it will be an 8x8 plane where all the entries are the same, the number of moves (or mpves with no progress).
There are two repetitions ...
- 76
6
votes
Accepted
How does the Alpha Zero's move encoding work?
Let's do the code, so all the details are down.
Encoding dictionary:
...
- 2,426
5
votes
Accepted
How do you encode a chess move in a neural network?
The number is 4672 from Google.
https://arxiv.org/pdf/1712.01815.pdf
...
- 1,411
5
votes
Accepted
How powerful is OpenAI's Gym and Universe in board games area?
OpenAI's Gym is a standardised API, useful for reinforcement learning, applied to a range of interesting environments many of which you can then access for free with little effort. It is very simple ...
- 30.3k
4
votes
Why were Chess experts surprised by the AlphaZero's victory against Stockfish?
MCTS for chess had been tried in the literature with little success. It was assumed AlphaGo's approach would never work on chess, maybe in Go but not in chess. Suddenly, Google announced the approach ...
- 1,411
4
votes
Accepted
Is the play of strong Chess AI easily distinguishable from human play?
AI programs that exist in today's world fall into the category of Narrow Intelligence. Narrow Intelligence
are easy to distinguish when compared to General Intelligence (ones that resemble more like ...
- 2,023
4
votes
Is the play of strong Chess AI easily distinguishable from human play?
There are three cases in which it is easily possible to distinguish strong AI play from the strong human play:
The AI is playing at superhuman skill level
This seems obvious, but I want to mention ...
- 1,684
4
votes
Accepted
What is the definition of rationality?
I've read that a simple reflex agent will not act rationally in a lot of environments. E.g. a simple reflex agent can't act rationally when driving a car as it needs previous perceptions to make ...
- 10.1k
3
votes
Accepted
Why was Go a harder game for an AI to master than Chess?
The branching factor is important, as it limits the effectiveness of search.
However, the branching factor in chess is already too high to effectively search without techniques that reduce the size ...
- 30.3k
3
votes
Accepted
Is there any value given to each chess piece in AlphaZero?
is there a value given for each piece (e.g. 1 for pawn, 3 for knight, 9 for queen, etc.) to train the algorithm, or does the algorithm learn this by himself?
No, there are no such explicit values ...
- 10.1k
3
votes
Can games be solved without an evaluation function?
Human chess and go experts clearly use evaluation functions. They do come up with moves that look sensible without evaluating the board position, but to validate these candidate moves they evaluate ...
- 4,205
3
votes
Why spend so much time and money to build AIs to play games?
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 ...
- 7,443
3
votes
Is there a way of representing the minimax algorithm mathematically?
A simple google search gives plenty of results.
If you have a look at the entry in wikipedia for Minimax it has mathematical representations as well as some basic pseudocode and tree representations ...
- 324
3
votes
How is AlphaZero different from Stockfish or Rybka?
Stockfish is free software (source while AlphaGo can only be used by employees at Deepmind. This is important, because it means all answers to this question can only rely on the AlphaGo paper. Some ...
- 1,055
3
votes
What is the definition of a heuristic function in the BayesChess paper?
By far the most common form of heuristic evaluation functions for Chess-playing (or, really, any game-playing) agents are simple linear functions. At least when we're talking about handcrafted ...
- 10.1k
3
votes
Combining deep reinforcement learning with alpha-beta pruning
Yes it's possible to to combine AlphaZero with Minimax methods (including alpha-beta pruning). AlphaZero itself is combination of Monte Carlo Tree Search (MCTS) and Deep Network, where MCTS is used ...
- 705
3
votes
Alpha Zero queen promotion
It means that there is no explicit coding of action choices to promote to queen, it is the default assumption if the underpromotion actions are not taken.
The Alpha Zero chess implementation can ...
- 30.3k
3
votes
Why does Alpha Zero's Neural Network flip the board to be oriented towards the current player?
I am not an expert in RL. I have been playing Go for some years.
Let's quote from AlphaZero's paper first:
Aside from
komi, the rules of Go are also invariant to colour transposition; this knowledge ...
- 131
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. ...
- 51
Only top scored, non community-wiki answers of a minimum length are eligible