Achieving corporative behavior in heterogeneous agents using hierarchic reinforcement learning-an approach to piano mover's problem

Autor:	Tomohiro Yoshida, Yukinori Kakazu, Yuko Ishiwaka, Hiroshi Yokoi
Rok vydání:	2004
Předmět:	business.industry Computer science Multi-agent system Piano Reinforcement learning Artificial intelligence Agent architecture business ComputingMethodologies_ARTIFICIALINTELLIGENCE
Zdroj:	IEEE International Conference on Systems, Man and Cybernetics.
DOI:	10.1109/icsmc.2002.1173252
Popis:	Our approach is to achieve the cooperative behavior of autonomous decentralized agents constructed with Q-Learning, which is a type of reinforcement learning. The piano mover's problem is employed. We propose the multi agent architecture that has an external agent and internal agents. Internal agents are heterogeneous and they can communicate with each other. The movement of the external agent depends on the composition of the actions of internal agents. According to learning its own shape by internal agents, it is expected that the agents avoid obstacles. We simulate our method on a two-dimensional continuous world. The results show the effect of our method.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::864000499771e7cfeaf658c97bfc8033 https://doi.org/10.1109/icsmc.2002.1173252 Zobrazit plný text záznamu