11–20 of 133 posts
Earlier quoted context omitted.
But only to complete a winning position.
From the abstract: > We annotate each board in the dataset with action-values provided by the powerful Stockfish 16 engine, leading to roughly 15 billion data points. So some of the learning data comes from Stockfish.
In training, traditional search is absolutely used to score positions.
In playing, search is not used. (*Except to finish out an already-won position.)
They do use Stockfish for playing thought … “To prevent some of these situations, we check whether the predicted scores for all top five moves lie above a win percentage of 99% and double-check this condition with Stockfish, and if so, use Stockfish’s top move (out of these) to have consistency in strategy across time-steps.”
But only to complete a winning position.
They note that though in the paper:
>Since transformers may learn to roll out iterative computation (which arises in search) across layers, deeper networks may hold the potential for deeper unrolls.
The path to AGI: 0. Have model A. 1. Use Monte Carlo with A to get supervised data. 2. Train model B with data from A. 3. Use Monte Carlo with B to get supervised data. 4. Train model C with data from B...
The "no-search" chess engine uses search (Stockfish) in in two ways:
1. To score positions in the training data. This is only training data, no search is performed when actually playing.
2. To play moves when the position has many options with a 99% win rate. This is to prevent pathological behavior in already won positions, and is not "meaningful" in the objective of grandmaster-level play.
Thus, "without search" is a valid description.