BriefGPT.xyz
Jun, 2011
贝叶斯多任务逆向强化学习
Bayesian multitask inverse reinforcement learning
HTML
PDF
Christos Dimitrakakis, Constantin Rothkopf
TL;DR
本文将逆向强化学习问题推广到多个任务，通过引入一定数量的结构化先验，我们将问题形式化为统计偏好提取。我们展示了我们的框架不仅允许我们从多个专家中有效地学习，而且还可以有效地区分每个专家的目标。
Abstract
We generalise the problem of
inverse reinforcement learning
to
multiple tasks
, from a set of demonstrations. Each demonstration may represent one expert trying to solve a different task. Alternatively, one may se
→