Predicting User Perception of Move Brilliance in Chess
This work addresses the need for AI in chess to appear more human-like and creative, though it is incremental as it applies existing neural network methods to a new domain-specific task.
The paper tackled the problem of predicting which chess moves are perceived as brilliant by humans, a previously unexamined aspect of chess aesthetics, and achieved an accuracy of 79% with a 50% base-rate, demonstrating that brilliant moves are not merely the best possible moves.
AI research in chess has been primarily focused on producing stronger agents that can maximize the probability of winning. However, there is another aspect to chess that has largely gone unexamined: its aesthetic appeal. Specifically, there exists a category of chess moves called ``brilliant" moves. These moves are appreciated and admired by players for their high intellectual aesthetics. We demonstrate the first system for classifying chess moves as brilliant. The system uses a neural network, using the output of a chess engine as well as features that describe the shape of the game tree. The system achieves an accuracy of 79% (with 50% base-rate), a PPV of 83%, and an NPV of 75%. We demonstrate that what humans perceive as ``brilliant" moves is not merely the best possible move. We show that a move is more likely to be predicted as brilliant, all things being equal, if a weaker engine considers it lower-quality (for the same rating by a stronger engine). Our system opens the avenues for computer chess engines to (appear to) display human-like brilliance, and, hence, creativity.