MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games 文章

ArXiv CS.AI2026-05-26NEWSen作者: Qian-Rong Li, Hung Guei, I-Chen Wu, Ti-Rong Wu
查看原文 →
关系图谱

MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games · 相关技术

相关技术

ginORMPLAneural networktree searchevalParts-of-Speech (POS) tagsPPRHISForFFIEffort Metric AttentionCISANNIAM