To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Cell Division Approach for Search Space in Reinforcement Learning |
|
Author |
Akira Notsu, Hiroyuki Wada, Katsuhiro Honda, Hidetomo Ichihashi |
| Citation |
Vol. 8 No. 6 pp. 18-21 |
|
Abstract |
In this paper, we propose a state and action search space division algorithm during learning process like a cell division. This algorithm is designed for search domain reduction and heuristic space segmentation. In this method, the most activated space segment is divided into new two segments during its learning. Appropriate search domain reduction can minimize the learning time and enables us to recognize the evolutionary process. This segmentation method is also designed for social simulation models. In a way, social space segmentation, such as language systems and culture, will be revealed by multi-agent social simulation with our method. |
|
Keywords |
Reinforcement Learning, Q-Learning, Cell Division, Agent Simulation |
|
URL |
