资源分类
》 资源 》论文》Automatic State Abstraction from Demonstration

Automatic State Abstraction from Demonstration

2019-11-12 | |  122 |   51 |   0

Abstract Learning from Demonstration (LfD) is a popular technique for building decision-making agents from human help. Traditional LfD methods use demonstrations as training examples for supervised learning, but complex tasks can require more examples than is practical to obtain. We present Abstraction from Demonstration (AfD), a novel form of LfD that uses demonstrations to infer state abstractions and reinforcement learning (RL) methods in those abstract state spaces to build a policy. Empirical results show that AfD is greater than an order of magnitude more sample ef?cient than just using demonstrations as training examples, and exponentially faster than RL alone.

上一篇：Increasing the Scalability of the Fitting of Generalised Block Models for Social Networks

下一篇：Learning Decision Rules from Data Streams

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...