BriefGPT.xyz
Nov, 2020
重新审视 Rainbow：促进更具启示性和包容性的深度强化学习研究
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
HTML
PDF
Johan S. Obando-Ceron, Pablo Samuel Castro
TL;DR
本文讨论在计算资源不足的情况下，重点研究小规模环境对于强化学习的科学洞见和降低贫困社区进入门槛的重要性，并通过更深入的研究Rainbow算法来证实此论点。
Abstract
Since the introduction of DQN, a vast majority of
reinforcement learning
research has focused on
reinforcement learning
with deep
neural networks
→