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 1906.01770cs.LGstat.ML
收藏

终身学习,不断变化的行动集

Lifelong Learning with a Changing Action Set

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Adobe Research(奥多比研究)

Yash Chandak, Georgios Theocharous, Chris Nota, Philip S. Thomas

摘要:

在许多现实世界的顺序决策问题中,可用的动作(决策)的数量可能会随着时间的推移而变化。虽然像灾难性遗忘,改变过渡动力学,改变奖励函数等问题已经在终身学习文献中得到了很好的研究,但行动集变化的设置仍然没有得到解决。在本文中,我们提出了一个算法,自主适应的行动集的大小随时间变化。为了解决这个开放的问题,我们将其分为两个可以迭代解决的问题:推断动作空间中的底层未知结构,并优化利用此结构的策略。我们证明了这种方法在大规模现实世界的终身学习问题的效率。

英文摘要:

In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed. In this paper, we present an algorithm that autonomously adapts to an action set whose size changes over time. To tackle this open problem, we break it into two problems that can be solved iteratively: inferring the underlying, unknown, structure in the space of actions and optimizing a policy that leverages this structure. We demonstrate the efficiency of this approach on large-scale real-world lifelong learning problems.

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。

↑