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 2005.07870cs.AI
收藏

深度强化学习中可迁移概念的学习

Learning Transferable Concepts in Deep Reinforcement Learning

Universidad de Los Andes(安第斯大学)

Diego Gomez, Nicanor Quijano, Luis Felipe Giraldo

摘要:

虽然人类和动物在一生中不断学习,并利用他们的经验来解决新的任务,但标准的深度强化学习方法一次只解决一个任务。因此,他们获得的信息很难在新的情况下重复使用。在这里,我们介绍了一个新的角度对利用先验知识来解决未来的任务的问题。我们发现,学习感官输入的离散表示可以提供一个高层次的抽象,这是常见的跨多个任务,从而促进信息的传递。特别是,我们表明,它是可以学习这样的表示自我监督,信息理论的方法。我们的方法是能够学习概念的机车和最优控制任务,提高样本效率在已知和未知的任务,开辟了一条新的路径,赋予人工智能体的泛化能力。

英文摘要:

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they acquire is hardly reusable in new situations. Here, we introduce a new perspective on the problem of leveraging prior knowledge to solve future tasks. We show that learning discrete representations of sensory inputs can provide a high-level abstraction that is common across multiple tasks, thus facilitating the transference of information. In particular, we show that it is possible to learn such representations by self-supervision, following an information theoretic approach. Our method is able to learn concepts in locomotive and optimal control tasks that increase the sample efficiency in both known and unknown tasks, opening a new path to endow artificial agents with generalization abilities.

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。

↑