arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.09448cs.LGcs.CLcs.CV
收藏

EC^2:面向具身控制的涌现通信

EC^2: Emergent Communication for Embodied Control

The University of Hong Kong(香港大学);Princeton University(普林斯顿大学);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)

Yao Mu, Shunyu Yao, Mingyu Ding, Ping Luo, Chuang Gan

AI总结:

本文提出 EC^2,通过涌现通信构建无监督视频语言并联合学习视频轨迹、涌现语言与自然语言表征,以提升少样本具身控制性能。

摘要:

具身控制要求智能体利用多模态预训练,以快速学习如何在新环境中行动;在这些环境中,视频演示包含低层感知与控制所需的视觉和运动细节,而语言指令则通过抽象的符号结构支持泛化。尽管近期方法采用对比学习来强制两种模态之间的对齐,但我们假设,更好地建模二者的互补差异可以产生更全面的表征,从而用于下游适配。为此,我们提出了面向具身控制的涌现通信(Emergent Communication for Embodied Control,EC^2),这是一种为少样本具身控制预训练视频-语言表征的新颖方案。其核心思想是通过涌现通信学习一种无监督的视频“语言”,从而在视频细节的语义与自然语言的结构之间建立桥梁。我们使用语言模型学习视频轨迹、涌现语言和自然语言的具身表征,随后利用该模型微调一个轻量级策略网络以进行下游控制。通过在 Metaworld 和 Franka Kitchen 具身基准上的大量实验,EC^2 在以视频和文本作为任务输入时,均表现出持续优于以往对比学习方法的性能。进一步的消融实验证实了涌现语言的重要性:它对视频学习和语言学习都有益,并且显著优于使用预训练视频字幕的做法。我们还对涌现语言进行了定量和定性分析,并讨论了未来方向,以更好地理解和利用具身任务中的涌现通信。

英文摘要:

Embodied control requires agents to leverage multi-modal pre-training to quickly learn how to act in new environments, where video demonstrations contain visual and motion details needed for low-level perception and control, and language instructions support generalization with abstract, symbolic structures. While recent approaches apply contrastive learning to force alignment between the two modalities, we hypothesize better modeling their complementary differences can lead to more holistic representations for downstream adaption. To this end, we propose Emergent Communication for Embodied Control (EC^2), a novel scheme to pre-train video-language representations for few-shot embodied control. The key idea is to learn an unsupervised "language" of videos via emergent communication, which bridges the semantics of video details and structures of natural language. We learn embodied representations of video trajectories, emergent language, and natural language using a language model, which is then used to finetune a lightweight policy network for downstream control. Through extensive experiments in Metaworld and Franka Kitchen embodied benchmarks, EC^2 is shown to consistently outperform previous contrastive learning methods for both videos and texts as task inputs. Further ablations confirm the importance of the emergent language, which is beneficial for both video and language learning, and significantly superior to using pre-trained video captions. We also present a quantitative and qualitative analysis of the emergent language and discuss future directions toward better understanding and leveraging emergent communication in embodied tasks.

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。

↑