arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08294cs.LG
收藏

Unicorn:使用通用的非策略代理进行持续学习

Unicorn: Continual Learning with a Universal, Off-policy Agent

DeepMind(深度思维);Technion Israel Institute of Technology(以色列理工学院);University of Michigan(密歇根大学)

Daniel J. Mankowitz, Augustin Žídek, André Barreto, Dan Horgan, Matteo Hessel, John Quan, Junhyuk Oh, Hado van Hasselt, David Silver, Tom Schaul

摘要:

一些现实世界的领域最好描述为一个单一的任务,但对其他人来说,这种观点是有限的。相反,一些任务的复杂性会随着智能体的能力而不断增长。在持续学习中,也称为终身学习,没有明确的任务界限或课程。随着学习代理变得越来越强大,持续学习仍然是阻碍快速进步的前沿领域之一。为了测试持续学习的能力,我们考虑了一个具有挑战性的3D域,其中包含一系列隐含的任务和稀疏的奖励。我们提出了一种新的代理架构称为独角兽,它表现出强大的持续学习,并优于几个基线代理建议域。代理实现这一点,联合表示和学习多个政策有效地,使用并行离策略学习设置。

英文摘要:

Some real-world domains are best characterized as a single task, but for others this perspective is limiting. Instead, some tasks continually grow in complexity, in tandem with the agent's competence. In continual learning, also referred to as lifelong learning, there are no explicit task boundaries or curricula. As learning agents have become more powerful, continual learning remains one of the frontiers that has resisted quick progress. To test continual learning capabilities we consider a challenging 3D domain with an implicit sequence of tasks and sparse rewards. We propose a novel agent architecture called Unicorn, which demonstrates strong continual learning and outperforms several baseline agents on the proposed domain. The agent achieves this by jointly representing and learning multiple policies efficiently, using a parallel off-policy learning setup.

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。

↑