刘昊辰
(2026-05-01 09:17):
#paper Not all Chess960 positions are equally complex. 本文以Stockfish 17.1为分析工具,对Chess960全部960种起始局面开展量化研究,证实并非所有Chess960局面复杂度均等;研究发现白方先手优势是国际象棋固有结构特征(均值+0.33±0.12兵),并提出信息成本度量S(n)量化决策复杂度,总复杂度区间2.6–17.2比特、决策不对称性-4.5~+4.2比特;传统国象起始局#518在复杂度与平衡性上均处于平均水平,无特殊最优地位,仅为历史文化选择。下载地址:https://arxiv.org/pdf/2512.14319
arXiv,
16 Dec 2025.
Not all Chess960 positions are equally complex
Marc Barthelemy
Abstract:
We analyze strategic complexity across all 960 Chess960 (Fischer Random Chess) starting positions. Stockfish evaluations reveal a near-universal first-move advantage for White ( pawns), indicating that the initiative is a robust structural feature of the game. To quantify decision difficulty, we introduce an information-based measure that captures the cumulative information required to identify optimal moves over the first plies. This measure decomposes into White and Black contributions, and , defining a total opening complexity and a decision asymmetry . Across the ensemble, ranges from to bits, while spans from to bits (mean ), showing that openings are nearly evenly split between those that burden White and those that burden Black, with a slight average excess complexity for White. Standard chess (position \#518, \texttt{RNBQKBNR}) exhibits near-average total complexity and asymmetry, yet lies far from the configuration that jointly minimizes evaluation imbalance and decision asymmetry. These results reveal a highly heterogeneous Chess960 landscape in which small rearrangements of back-rank pieces can substantially alter strategic depth and competitive balance. The classical starting position--despite centuries of refinement--appears not as an extremum, but as one configuration among many in a broad statistical ensemble.