arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.03153cs.LGcs.AIcs.ROcs.SYeess.SY
收藏

MBMF:基于模型的先验用于无模型强化学习

MBMF: Model-Based Priors for Model-Free Reinforcement Learning

University of California Berkeley(加州大学伯克利分校)

Somil Bansal, Roberto Calandra, Kurtland Chua, Sergey Levine, Claire Tomlin

AI总结:

本文提出一种结合模型与无模型强化学习的方法,通过学习概率动力学模型作为先验,提升数据效率和成本效益。

摘要:

强化学习主要分为无模型和有模型两种范式。每种范式都有其优势和局限性,并已成功应用于适合其相应优势的真实世界领域。本文提出一种新方法,旨在弥合这两种范式的差距。我们通过学习概率动力学模型,并将其作为交织的无模型优化的先验,结合两种范式的优点,从而实现数据高效和成本节约。结果表明,我们的方法在性能上优于纯有模型和纯无模型方法,以及简单切换范式的方法。

英文摘要:

Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to real world domains that are appropriate to its corresponding strengths. In this paper, we present a new approach aimed at bridging the gap between these two paradigms. We aim to take the best of the two paradigms and combine them in an approach that is at the same time data-efficient and cost-savvy. We do so by learning a probabilistic dynamics model and leveraging it as a prior for the intertwined model-free optimization. As a result, our approach can exploit the generality and structure of the dynamics model, but is also capable of ignoring its inevitable inaccuracies, by directly incorporating the evidence provided by the direct observation of the cost. Preliminary results demonstrate that our approach outperforms purely model-based and model-free approaches, as well as the approach of simply switching from a model-based to a model-free setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑