arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.07530cs.LGcs.AIstat.ML
收藏

自组织映射作为强化学习的存储和传输机制

Self-Organizing Maps as a Storage and Transfer Mechanism in Reinforcement Learning

Singapore University of Technology and Design(新加坡科技设计大学)

Thommen George Karimpanal, Roland Bouffanais

摘要:

重用来自先前学习的任务(源任务)的信息用于学习新任务(目标任务)的想法具有显著提高样本效率的潜力强化学习代理。在这项工作中,我们描述了一种方法来简洁地存储和表示学习的任务知识,并通过允许它引导探索的代理,而它学习新的任务,并重用它。为了做到这一点,我们使用的相似性的措施,直接定义在空间的参数化表示的价值函数。这种相似性度量也被用来作为一个不断增长的自组织地图算法,这是同时用于使以前获得的任务知识的存储在一个自适应和可扩展的方式的一个变体的基础上,我们经验验证我们的方法在模拟导航环境中,并讨论这种方法可能的扩展以及潜在的应用,它可能是特别有用的。

英文摘要:

The idea of reusing information from previously learned tasks (source tasks) for the learning of new tasks (target tasks) has the potential to significantly improve the sample efficiency reinforcement learning agents. In this work, we describe an approach to concisely store and represent learned task knowledge, and reuse it by allowing it to guide the exploration of an agent while it learns new tasks. In order to do so, we use a measure of similarity that is defined directly in the space of parameterized representations of the value functions. This similarity measure is also used as a basis for a variant of the growing self-organizing map algorithm, which is simultaneously used to enable the storage of previously acquired task knowledge in an adaptive and scalable manner.We empirically validate our approach in a simulated navigation environment and discuss possible extensions to this approach along with potential applications where it could be particularly useful.

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。

↑