arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.16232cs.LGcs.ROstat.ML
收藏

基于时间变分推理的机器人技能学习

Learning Robot Skills with Temporal Variational Inference

Facebook AI Research(脸书人工智能研究院);Carnegie Mellon University(卡内基梅隆大学)

Tanmay Shankar, Abhinav Gupta

摘要:

在本文中,我们解决了发现机器人的选项,从演示中的无监督的方式。具体来说,我们提出了一个框架,共同学习低级别的控制政策和更高级别的政策,如何使用它们从演示的机器人执行各种任务。通过将选项表示为连续的潜变量,我们将学习这些选项的问题框架为潜变量推理。然后,我们提出了一个时间公式的变分推理的基础上的时间因式分解的轨迹似然,这使我们能够推断选项在无监督的方式。我们展示了我们的框架在三个机器人演示数据集上学习这些选项的能力。

英文摘要:

In this paper, we address the discovery of robotic options from demonstrations in an unsupervised manner. Specifically, we present a framework to jointly learn low-level control policies and higher-level policies of how to use them from demonstrations of a robot performing various tasks. By representing options as continuous latent variables, we frame the problem of learning these options as latent variable inference. We then present a temporal formulation of variational inference based on a temporal factorization of trajectory likelihoods,that allows us to infer options in an unsupervised manner. We demonstrate the ability of our framework to learn such options across three robotic demonstration datasets.

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。

↑