Hierarchical reinforcement learning based on ant colony optimization algorithm

Agent interacts with the environment to perform their assigned tasks in autonomous systems. Using hierarchical reinforcement learning technology helps the agent to improve learning efficiency in the large and complex environment. This paper put forward a new method to find subgoal. It used the rate...

Full description

Saved in:
Bibliographic Details
Published inJi suan ji ying yong yan jiu Vol. 31; no. 11; pp. 3214 - 3220
Main Authors Zhou, Xiao-Ke, Sun, Zhi-Yi, Peng, Zhi-Ping
Format Journal Article
LanguageChinese
Published 01.11.2014
Subjects
Agents (artificial intelligence)
Algorithms
Ant colony optimization
Authentication
Learning
Reinforcement
Roughness
Tasks
Online AccessGet full text

Cover

More Information
Summary:Agent interacts with the environment to perform their assigned tasks in autonomous systems. Using hierarchical reinforcement learning technology helps the agent to improve learning efficiency in the large and complex environment. This paper put forward a new method to find subgoal. It used the rate of change of pheromone which ants leaved in ergodic process to define the roughness, and used the roughness to define the sub-goals. It used the found subgoals to create abstract agent in order to explore more effective. The experimental results show that this method can significantly improve the learning performance. Authentication algorithm in a taxi environmental performance, experimental results show that this method can significantly improve the learning efficiency of agent.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
content type line 23
ObjectType-Feature-2
ISSN:1001-3695
DOI:10.3969/j.issn.1001-3695.2014.11.003