72
votes
Accepted
How does an AI like ChatGPT answer a question in a subject which it may not know?
ChatGPT is a large language model. That means it's very good at stringing together words in ways that humans tend to use them. It's able to construct sentences that are grammatically correct and sound ...
- 2,915
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 ...
- 32.9k
20
votes
How does an AI like ChatGPT answer a question in a subject which it may not know?
ChatGPT does not actually know anything. But more importantly even, it does not know this fact! Hence, it does not know that it does not know.
It is only good at combining text.
- 309
15
votes
How does an AI like ChatGPT answer a question in a subject which it may not know?
ChatGPT and other GPT-based machine learning models don't actually know anything in the sense you're thinking of. ChatGPT is a distant descendant of Markov chain text generators such as Dissociated ...
- 420
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
8
votes
Is there any board game where a human can still beat an AI?
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).
...
- 1,800
6
votes
Accepted
Is there any board game where a human can still beat an AI?
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 ...
- 4,272
5
votes
Accepted
How should I represent the input to a neural network for the games of tic-tac-toe, checkers or chess?
When you are working with neural networks, as long as the data is there, the neural network is usually able to learn how to process it into a useful result.
However, you usually also want to keep the ...
- 873
3
votes
Which value to propagate in Monte Carlo Tree Search in a non-zero-sum game?
In theory: yes, you can backpropagate any sort of scores you want to maximise. They don't have to be restricted to just a small, discrete set of values such as $\{-1, 0, 1\}$, and also do not have to ...
- 10.4k
3
votes
How should I represent the input to a neural network for the games of tic-tac-toe, checkers or chess?
The basis of reinforcement learning methods is to give each (game) state (or action) a value that somehow represents how good that state (or action) is. To store these values we could use something as ...
- 562
3
votes
How to deal with a huge action space, where, at every step, there is a variable number of legal actions?
One way I can think of is to redefine "actions" in a game to make them more fragmented, in such a way that a player has multiple actions per turn. In chess, for example, we can define an action as ...
- 171
2
votes
Is there any board game where a human can still beat an AI?
Artificially intelligent computer programs should be able to be at the same level or beat humans at every game that we play. This is because games follow rules that are scriptable, and artificial ...
2
votes
Accepted
Neural Network output for the game of Checkers
Correction regarding policy encoding
The policy encoding you propose for Chess is not the one used by the original AlphaZero and would not work. The network needs to output a policy distribution over ...
- 483
2
votes
How should I represent the input to a neural network for the games of tic-tac-toe, checkers or chess?
Representation of states is very important to prepare the data for the neural networks. You can try a different way and pick which fit best in your case.
You can use 18 neurons as input where each ...
- 253
2
votes
Accepted
How to account for a numeric variable in a state in RL?
You don't have "9 possible states" in your problem, you have those 9 board squares multiplied by all possible values that the numbers within them can take, in all combinations. If those are ...
- 32.9k
2
votes
How does an AI like ChatGPT answer a question in a subject which it may not know?
The original question asked about "an AI" generally, yet most of the responses here focus on OpenAI's ChatGPT specifically. Seems like the answer would depend on the specific type of AI ...
- 121
1
vote
Accepted
AlphaZero Chess: High portion of "draws" during first rounds of self-play hampers learning
First intuition
I wrote a quick script to test the outcome distribution of random chess games: I get about 7% wins for black and white each, so 14% non-drawn games. The MCTS should still be able to ...
- 483
1
vote
MCTS: Units away from the action
Monte Carlo Tree Search is searching for the action with the best expected reward. If the reward is determined by whether it wins or losses, then all winning moves are equal and one will be selected ...
- 111
1
vote
MCTS: Units away from the action
It is very nice and I recommend others to play with your code. Really nice. Did I get it right that the Carthaginian are the ones with extra power and you refer to them as the AI? It seems that the ...
- 141
1
vote
MCTS: Units away from the action
One option is that the RL is not there yet, you may need to continue with the training, or maybe add to the win/lose reward some tiny "hints" what is a good move (0.001 when you eat an enemy,...
- 141
1
vote
Monte Carlo Tree Search for Robo Rally AI
Have looked at the game description.
MCTS can be a very good choice, as far as I can tell.
The action that you take at each phase is selecting five cards from the nine you have and placing them face ...
- 141
1
vote
Accepted
MCTS with multi actions
Yes, for MCTS this is no problem at all. In fact it is slightly more annoying for minimax/alpha-beta based engines, because there we usually like (if possible) to use efficient negamax implementations ...
- 10.4k
1
vote
Scrabble rack observation with MuZero
Use one hot encoding for each position, shape $(7, 27)$.
Stack these two dimensions, shape $(189)$.
Tile (replicate) this vector into images of the same resolution, now shape $(15, 15, 189)$
Stack ...
- 136
1
vote
Strategy for playing a board game with Minimax algorithm
I'm not familiar with your game so I can't tell you what a good heuristic woul be in your specific case, but I can give you some advice on how to look for a good heuristic function.
As a rule of thumb,...
- 26
1
vote
How do I write a good evaluation function for a board game?
Based on your description, I'd maximize the following terms:
i
-max(f - 10 - (MAX_FIELD_INDEX - i), 0) - assuming consumption ...
- 563
1
vote
How to design a good evaluation function for a go-like game?
If you have the best combination of distance between the stones, you should choose the best move to win. In this case, you have to be close to where your opponent plays. It is best to do this by ...
- 21
Only top scored, non community-wiki answers of a minimum length are eligible