Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions 文章

ArXiv CS.AI2026-06-03NEWSen作者: Bingxu Liu, Jiashun Liu, Johan Obando-Ceron, Hao Wang, Runze Liu, Pablo Samuel Castro, Aaron Courville, Ling Pan
查看原文 →
关系图谱

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions · 相关技术

相关技术

Gaussian kernelGTRPPOGaussian Trust Region Policy OptimizationProximal Policy Optimization