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.
toiselle kielelle
lähdeaineistosta
arxiv.org
Tärkeimmät oivallukset
by Yu Chen,Xian... klo arxiv.org 02-29-2024
https://arxiv.org/pdf/2402.18159.pdfSyvällisempiä Kysymyksiä