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 2003.08165cs.NEcs.CVcs.LG
收藏

自我解释代理的神经进化

Neuroevolution of Self-Interpretable Agents

Google Brain(谷歌大脑);Google Japan(谷歌日本)

Yujin Tang, Duong Nguyen, David Ha

摘要:

不注意视盲是一种心理现象,导致一个人错过的东西在平原视线。这是感知中选择性注意力的结果,它让我们保持专注于世界的重要部分,而不会从无关的细节中分心。出于选择性注意,我们研究的属性,人工代理感知世界通过镜头的自我注意力瓶颈。通过限制仅访问一小部分视觉输入,我们表明他们的策略可以在像素空间中直接解释。我们发现神经进化是训练基于视觉的强化学习(RL)任务的自我注意力架构的理想选择,使我们能够整合可以包括对我们的代理有用的离散,不可微操作的模块。我们认为,自我注意力具有类似的属性作为间接编码,在这个意义上,大型隐式权重矩阵是从少量的关键查询参数生成的,从而使我们的代理解决具有挑战性的基于视觉的任务与至少1000倍的参数比现有的方法。由于我们的代理只关注关键任务的视觉提示,因此它们能够推广到任务无关元素被修改而传统方法失败的环境。我们的结果和源代码的视频可在https://attentionagent.github.io/上获得

英文摘要:

Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain focused on important parts of our world without distraction from irrelevant details. Motivated by selective attention, we study the properties of artificial agents that perceive the world through the lens of a self-attention bottleneck. By constraining access to only a small fraction of the visual input, we show that their policies are directly interpretable in pixel space. We find neuroevolution ideal for training self-attention architectures for vision-based reinforcement learning (RL) tasks, allowing us to incorporate modules that can include discrete, non-differentiable operations which are useful for our agent. We argue that self-attention has similar properties as indirect encoding, in the sense that large implicit weight matrices are generated from a small number of key-query parameters, thus enabling our agent to solve challenging vision based tasks with at least 1000x fewer parameters than existing methods. Since our agent attends to only task critical visual hints, they are able to generalize to environments where task irrelevant elements are modified while conventional methods fail. Videos of our results and source code available at https://attentionagent.github.io/

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。

↑