arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00243cs.ROcs.AIcs.CVcs.LGcs.SYeess.SY
收藏

基于状态观测器的视频对抗性模仿学习

Adversarial Imitation Learning from Video using a State Observer

The University of Texas at Austin(德克萨斯大学奥斯汀分校);Army Research Laboratory(陆军研究实验室);Sony AI(索尼人工智能研究院)

Haresh Karnan, Garrett Warnell, Faraz Torabi, Peter Stone

摘要:

模仿学习研究界最近在实现使人工智能体能够仅从视频演示中模仿行为的目标方面取得了重大进展。然而,目前的国家的最先进的方法开发的这个问题表现出高样本的复杂性,部分原因是由于视频观测的高维性质。为了解决这个问题,我们在这里介绍一个新的算法,称为视觉生成对抗模仿从观察使用状态观察VGAIfO-SO。在其核心,VGAIfO-SO试图解决样本效率低下,使用一种新的,自我监督的状态观测器,它提供了估计的低维本体感觉状态表示从高维图像。我们的实验表明,在几个连续的控制环境中,VGAIFO-SO是更有效的样本比其他IfO算法在学习视频只有演示,有时甚至可以实现性能接近生成对抗模仿观察(GAIFO)算法,有特权访问演示的本体感受状态信息。

英文摘要:

The imitation learning research community has recently made significant progress towards the goal of enabling artificial agents to imitate behaviors from video demonstrations alone. However, current state-of-the-art approaches developed for this problem exhibit high sample complexity due, in part, to the high-dimensional nature of video observations. Towards addressing this issue, we introduce here a new algorithm called Visual Generative Adversarial Imitation from Observation using a State Observer VGAIfO-SO. At its core, VGAIfO-SO seeks to address sample inefficiency using a novel, self-supervised state observer, which provides estimates of lower-dimensional proprioceptive state representations from high-dimensional images. We show experimentally in several continuous control environments that VGAIfO-SO is more sample efficient than other IfO algorithms at learning from video-only demonstrations and can sometimes even achieve performance close to the Generative Adversarial Imitation from Observation (GAIfO) algorithm that has privileged access to the demonstrator's proprioceptive state information.

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。

↑