arXiv 2008.127602020-08-28cs.CVcs.AIcs.LGcs.MAcs.RO

AllenAct：一个并行AI研究框架

AllenAct: A Framework for Embodied AI Research

UIUC（伊利诺伊大学厄巴纳-香槟分校）；University of Washington（华盛顿大学）

Luca Weihs, Jordi Salvador, Klemen Kotar, Unnat Jain, Kuo-Hao Zeng, Roozbeh Mottaghi, Aniruddha Kembhavi

摘要：

人工智能领域，其中代理人通过自我中心的观察与环境交互来学习完成任务，随着深度强化学习的出现以及计算机视觉，NLP和机器人社区的兴趣增加，已经经历了实质性的增长。大量模拟环境（如AI 2-THOR、Habitat和CARLA）、任务（如点导航、指令遵循和嵌入式问答）和相关排行榜的创建促进了这种增长。虽然这种多样性是有益的和有机的，但它也使社区变得支离破碎：需要大量的努力来做一些简单的事情，比如在一个环境中训练模型并在另一个环境中测试它。这阻碍了良好的科学。我们介绍AllenAct，这是一个模块化和灵活的学习框架，旨在专注于人工智能研究的独特要求。AllenAct为越来越多的嵌入式环境、任务和算法提供一流的支持，提供最先进模型的复制品，并包括大量文档、教程、启动代码和预训练模型。我们希望我们的框架能够使人工智能更容易获得，并鼓励新的研究人员加入这个令人兴奋的领域。该框架可在以下网址访问：https://allenact.org/

英文摘要：

The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with the advent of deep reinforcement learning and increased interest from the computer vision, NLP, and robotics communities. This growth has been facilitated by the creation of a large number of simulated environments (such as AI2-THOR, Habitat and CARLA), tasks (like point navigation, instruction following, and embodied question answering), and associated leaderboards. While this diversity has been beneficial and organic, it has also fragmented the community: a huge amount of effort is required to do something as simple as taking a model trained in one environment and testing it in another. This discourages good science. We introduce AllenAct, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research. AllenAct provides first-class support for a growing collection of embodied environments, tasks and algorithms, provides reproductions of state-of-the-art models and includes extensive documentation, tutorials, start-up code, and pre-trained models. We hope that our framework makes Embodied AI more accessible and encourages new researchers to join this exciting area. The framework can be accessed at: https://allenact.org/

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。

摘要：

英文摘要：

相关论文