.png){kind=icon}
返回
Improving reinforcement learning by using sequence trees
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-010-5182-y.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes a novel approach to discover options in the form of stochastic conditionally terminating sequences; it shows how such sequences can be integrated into the reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure during the learning process. The constructed tree facilitates the process of identifying frequently used action sequences together with states that are visited during the execution of such sequences. The tree is constantly updated and used to implicitly run corresponding options. The effectiveness of the method is demonstrated empirically by conducting extensive experiments on various domains with different properties.
Keyword:
Reinforcement learning
Options
Conditionally terminating sequences
Temporal abstractions
Semi-Markov decision processes
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Physical Activity in Community‐Dwelling Stroke Survivors and a Healthy Population Is Not Explained by Motor Function Only.png)
PM&R
PM&RIF0
PREAI
分享收藏
5′ Flanking region of immunoglobulin heavy chain constant region genes displays length heterogeneity in germlines of inbred mouse strainsCell
CellIF0
PREAI
分享收藏分享收藏
查看更多内容