arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.02871cs.LGcs.RO
收藏

论约定在自适应人机协作中的关键作用

On the Critical Role of Conventions in Adaptive Human-AI Collaboration

Stanford University(斯坦福大学);Princeton University(普林斯顿大学)

Andy Shih, Arjun Sawhney, Jovana Kondic, Stefano Ermon, Dorsa Sadigh

摘要:

人类可以在协作任务(例如打篮球)中快速适应新的合作伙伴,因为他们了解任务的哪些基本技能(例如如何运球,如何投篮)可以在新的合作伙伴中进行。人类也可以通过继承他们已经形成的惯例(例如举手示意传球)来快速适应与相同伙伴的类似任务,而无需从头开始学习协调。为了与人类无缝协作,人工智能智能体也应该快速适应新的合作伙伴和新的任务。然而,目前的方法并没有试图区分任务固有的复杂性和合作伙伴使用的惯例,更普遍的是,很少关注利用惯例来适应新的环境。在这项工作中,我们提出了一个学习框架,挑逗除了规则依赖的代表性,从公约依赖的代表性的原则性的方式。我们表明,在某些假设下,我们的规则依赖的表示是一个足够的统计分布在最佳对策的合作伙伴。使用这种分离的表示,我们的代理能够快速适应新的合作伙伴,并协调与旧的合作伙伴在新的任务在一个zero-shot的方式。我们的实验验证我们的方法在三个不同的复杂性的协作任务:上下文多臂强盗,块放置任务,和纸牌游戏Hanabi。

英文摘要:

Humans can quickly adapt to new partners in collaborative tasks (e.g. playing basketball), because they understand which fundamental skills of the task (e.g. how to dribble, how to shoot) carry over across new partners. Humans can also quickly adapt to similar tasks with the same partners by carrying over conventions that they have developed (e.g. raising hand signals pass the ball), without learning to coordinate from scratch. To collaborate seamlessly with humans, AI agents should adapt quickly to new partners and new tasks as well. However, current approaches have not attempted to distinguish between the complexities intrinsic to a task and the conventions used by a partner, and more generally there has been little focus on leveraging conventions for adapting to new settings. In this work, we propose a learning framework that teases apart rule-dependent representation from convention-dependent representation in a principled way. We show that, under some assumptions, our rule-dependent representation is a sufficient statistic of the distribution over best-response strategies across partners. Using this separation of representations, our agents are able to adapt quickly to new partners, and to coordinate with old partners on new tasks in a zero-shot manner. We experimentally validate our approach on three collaborative tasks varying in complexity: a contextual multi-armed bandit, a block placing task, and the card game Hanabi.

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。

↑