BriefGPT.xyz
Oct, 2019
自适应上下文强化学习
Self-Paced Contextual Reinforcement Learning
HTML
PDF
Pascal Klink, Hany Abdulsamad, Boris Belousov, Jan Peters
TL;DR
研究智能自主机器人如何通过新方法中的相对熵奖励学习算法来提高样本效率并使学习扩展到更广泛和尖锐的任务上。
Abstract
generalization
and
adaptation
of learned skills to novel situations is a core requirement for intelligent
autonomous robots
. Although cont
→