Switching for Functional Localization of Genetic Network Programming

Eto, Shinji; Hirasawa, Kotaro; Hu, Jingle

doi:10.1109/icmla.2005.61

Cited by 1 publication

(1 citation statement)

References 6 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because it has many predictable and unpredictable opportunities to act, the agent must autonomously decide which action to execute out of many possible actions at each opportunity while consuming energy. Relevant research to solve this problem is proposed by Eto et al [9], which uses several sub-GNPs for a single task separately and combining them by the functional switching method. The paper shows that even if the optimal sub-GNPs for the single task are supposed to be found, the combination of the sub-GNPs is quite diffi cult.…”

Section: Autonomymentioning

confidence: 99%

A multitasks learning approach to autonomous agent based on Genetic Network Programming

Yang

Mabu

Hirasawa

2012

2012 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

The standard methodology in machine learning is to learn one problem at a time. But, many real-world problems are complex and have multitasks, and it is a bit hard to learn them well by one machine learning approach. So, the simultaneous learning of several tasks has been considered, that is, so-called multitask learning. This paper describes a new approach to the autonomous agent problem using the multitask learning scheme based on Genetic Network Programming (GNP), called ML-GNP, where each GNP is used to learn one corresponding task. ML-GNP has some charateristics, such as distribution, interaction and autonomy, which are helpful for learning multitask problems. The experimental results illustrate that ML-GNP can give much better performance than learning all the tasks of the problem by one GNP algorithm.• A start node indicates the fi rst node to be executed.

show abstract

Section: Autonomymentioning

confidence: 99%