The paper introduces RS-DisRL for risk-sensitive RL with static LRM and general function approximation. It covers model-based and model-free approaches, providing theoretical guarantees for efficient learning. The work addresses challenges in sample complexity and extends to value function approximation.
A otro idioma
del contenido fuente
arxiv.org
Ideas clave extraídas de
by Yu Chen,Xian... a las arxiv.org 02-29-2024
https://arxiv.org/pdf/2402.18159.pdfConsultas más profundas