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 1702.08360cs.LG
收藏

神经地图:用于深度强化学习的结构化记忆

Neural Map: Structured Memory for Deep Reinforcement Learning

Carnegie Mellon University(卡内基梅隆大学)

Emilio Parisotto, Ruslan Salakhutdinov

摘要:

在部分可观察的环境中实现智能推理的一个关键组成部分是记忆。尽管如此重要,深度强化学习(DRL)代理到目前为止使用相对简单的内存架构,克服部分可观察性的主要方法是过去k帧的时间卷积或LSTM层。最近的工作(Oh等人,2016)已经通过使用存储器网络超越了这些架构,该存储器网络可以允许在过去的k帧上更复杂的寻址方案。但是,即使这些架构也是不令人满意的,因为它们仅限于记住来自最后k帧的信息。在本文中,我们开发了一个内存系统,具有自适应的写操作,是定制的DRL代理通常与各种3D环境。这种架构被称为神经地图,它使用空间结构化的2D记忆图像来学习在长时间滞后的情况下存储有关环境的任意信息。我们凭经验证明,神经地图超越了以前的DRL记忆在一组具有挑战性的2D和3D迷宫环境,并表明它能够推广到在训练过程中没有看到的环境。

英文摘要:

A critical component to enabling intelligent reasoning in partially observable environments is memory. Despite this importance, Deep Reinforcement Learning (DRL) agents have so far used relatively simple memory architectures, with the main methods to overcome partial observability being either a temporal convolution over the past k frames or an LSTM layer. More recent work (Oh et al., 2016) has went beyond these architectures by using memory networks which can allow more sophisticated addressing schemes over the past k frames. But even these architectures are unsatisfactory due to the reason that they are limited to only remembering information from the last k frames. In this paper, we develop a memory system with an adaptable write operator that is customized to the sorts of 3D environments that DRL agents typically interact with. This architecture, called the Neural Map, uses a spatially structured 2D memory image to learn to store arbitrary information about the environment over long time lags. We demonstrate empirically that the Neural Map surpasses previous DRL memories on a set of challenging 2D and 3D maze environments and show that it is capable of generalizing to environments that were not seen during training.

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。

↑