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 1909.04607cs.AIcs.LG
收藏

发现有用的问题作为辅助任务

Discovery of Useful Questions as Auxiliary Tasks

University of Michigan, Ann Arbor(密歇根大学安娜堡分校);DeepMind(深度思维)

Vivek Veeriah, Matteo Hessel, Zhongwen Xu, Richard Lewis, Janarthanan Rajendran, Junhyuk Oh, Hado van Hasselt, David Silver, Satinder Singh

摘要:

可以说,智能代理应该能够发现自己的问题,以便在为他们学习答案的过程中,他们学习到意想不到的有用知识和技能;这与机器学习的大部分焦点不同,机器学习的焦点是代理学习外部定义的问题的答案。我们提出了一种新的方法,强化学习(RL)代理发现问题制定为一般价值函数或GVF,一个相当丰富的形式的知识表示。具体来说,我们的方法使用非近视元梯度来学习GVF问题,以便学习它们的答案,作为辅助任务,诱导RL代理所面临的主要任务的有用表示。我们证明,辅助任务的基础上发现的GVF是足够的,对自己的,建立表示,支持主要任务的学习,他们这样做比流行的手工设计的辅助任务,从文献。此外,我们显示,在雅达利2600视频游戏的背景下,如何辅助任务,元学习的主要任务,可以提高数据效率的演员评论家代理。

英文摘要:

Arguably, intelligent agents ought to be able to discover their own questions so that in learning answers for them they learn unanticipated useful knowledge and skills; this departs from the focus in much of machine learning on agents learning answers to externally defined questions. We present a novel method for a reinforcement learning (RL) agent to discover questions formulated as general value functions or GVFs, a fairly rich form of knowledge representation. Specifically, our method uses non-myopic meta-gradients to learn GVF-questions such that learning answers to them, as an auxiliary task, induces useful representations for the main task faced by the RL agent. We demonstrate that auxiliary tasks based on the discovered GVFs are sufficient, on their own, to build representations that support main task learning, and that they do so better than popular hand-designed auxiliary tasks from the literature. Furthermore, we show, in the context of Atari 2600 videogames, how such auxiliary tasks, meta-learned alongside the main task, can improve the data efficiency of an actor-critic agent.

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。

↑