Stable Deep Reinforcement Learning via Isotropic Gaussian Representations 文章

ArXiv CS.AI2026-06-06NEWSen作者: Ali Saheb Pasand, Johan Obando-Ceron, Aaron Courville, Pouya Bashivan, Pablo Samuel Castro

查看原文 →

Stable Deep Reinforcement Learning via Isotropic Gaussian Representations · 相关技术

相关技术

isotropic Gaussian distribution Sketched Isotropic Gaussian Regularization linear readouts time-varying targets isotropic Gaussian embeddings non-stationary targets non-stationarity Deep Reinforcement Learning (DRL)