Cross-Entropy Games and Frost Training 文章

ArXiv CS.AI2026-05-28NEWSen作者: Arthur Renard, Franck Gabriel, Valentin Hartmann, Cl\'ement Hongler
机器人
查看原文 →
关系图谱

Cross-Entropy Games and Frost Training · 相关技术

相关技术

maximum-likelihood infillingGRPO trainingGreedy Coordinate GradientCross-Entropy GamesLLM-as-a-JudgeMonte Carlo-based policy optimizationFrost Training