It’s very iterative and mechanical. I would often struggle with ladders in blitz games because they require you to project a diagonal line across a large board with extreme precision. Misjudging by half a square could be fatal. And you also must reassess the ladder whenever a stone is placed near that invisible diagonal line.
That’s a great idea. I think some sort of CoT would definitely help.
Or in the case of KataGo, a dedicated Ladder-solver that serves as the input to the neural network is more than sufficient. IIRC all ladders of liberties 4 or less are solved by the dedicated KataGo solver.
It's not clear why these adversarial examples pop up yet IMO. It's not an issue of search depth or breadth either, it seems like an instinct thing.
MCTS evaluates current position using predictions of future positions.
To understand value of ladders the algorithm would need iteratively analyse just the current layout of the pieces on the board.
Apparently the value of ladders is hard to infer from probabilisticrvsample of predictions of the future.
Ladders were accidental human discovery just because our attention is drawn to patterns. It just happens to be that they are valuable and can be mechanistically analyzed and evaluated. AI so far struggles with 1 shot outputting solutions that would require running small iterative program to calculate.
Can MCTS dynamically determine that it needs to analyze a certain line to a much higher depth than normal due to the specifics of the situation?
That’s the type of flexible reflection that is needed. I think most people would agree that the hard-coded ladder solver in Katago is not ideal, and feels like a dirty hack. The system should learn when it needs to do special analysis, not have us tell it when to. It’s good that it works, but it’d be better if it didn’t need us to hard-code such knowledge.
Humans are capable of realizing what a ladder is on their own (even if many learn from external sources). And it definitely isn’t hard-coded into us :)
Traditional MCTS analyzes each line all the way to endgame.
I believe neural-net based MCTS (ex: AlphaZero and similar) use the neural-net to determine how deep any line should go. (Ex: which moves are worth exploring? Well, might as well have that itself part of the training / inference neural net).
In my understanding, in KataGo, the decision of how long to follow a line is made solely by MCTS via its exploration/exploitation components. These in turn are influence by the policy/value outputs of the DCNN. So in practical terms, your statement might just be called true.
The raw net output includes some values that could be used in addition, but they are not used. I don't know if they were ever looked at closely for this purpose.
Maybe solving ladders is iterative? Once they make chain-of-thought version of AlphaZero it might figure them out.