期刊
2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC)
卷 -, 期 -, 页码 3530-3534出版社
IEEE
DOI: 10.1109/SMC.2018.00597
关键词
Growing self-organizing map; Reinforcement learning; Learning optimization; Online learning
资金
- JSPS KAKENHI [JP15K00344]
In reinforcement learning, since the learning cycles are set by the designer, this drawback greatly affects the learning efficiency. In this research, we adaptively change the learning cycles of online reinforcement learning systems to acquire a necessary and sufficient set of states for them. We used a growing self-organizing map to estimate the state for fast learning speed. In conventional methods, a calculation is performed more often than necessary, but in our proposed method, calculations that are unnecessary for learning are minimized based on the state transition. We demonstrate that the proposed method finishes learning quickly by the inverted pendulum task and, based on our experiment results, find that an approach that adaptively shortens or lengthens the learning cycle is suitable for reinforcement learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据