Transfer Learning Method Using Ontology for Heterogeneous Multi-agent Reinforcement Learning

Abstract

This paper presents a framework, called the knowledge co-creation framework (KCF), for heterogeneous multiagent robot systems that use a transfer learning method. A multiagent robot system (MARS) that utilizes reinforcement learning and a transfer learning method has recently been studied in realworld situations. In MARS, autonomous agents obtain behavior autonomously through multi-agent reinforcement learning and the transfer learning method enables the reuse of the knowledge of other robots’ behavior, such as for cooperative behavior. Those methods, however, have not been fully and systematically discussed. To address this, KCF leverages the transfer learning method and cloud-computing resources. In prior research, we developed ontology-based inter-task mapping as a core technology for hierarchical transfer learning (HTL) method and investigated its effectiveness in a dynamic multi-agent environment. The HTL method hierarchically abstracts obtained knowledge by ontological methods. Here, we evaluate the effectiveness of HTL with a basic experimental setup that considers two types of ontology: action and state.

Authors and Affiliations

Hitoshi Kono, Akiya Kamimura, Kohji Tomita, Yuta Murata, Tsuyoshi Suzuki

Keywords

Related Articles

Towards an SOA Architectural Model for AAL-Paas Design and Implimentation Challenges

Ambient Assisted Living (AAL) systems main purpose is to improve the quality of life of special groups of people, including the elderly and people with physical disabilities. Driven by the critical ongoing changes in all...

A Review of Embedding Hexagonal Cells in the Circular and Hexagonal Region of Interest

Hexagonal cells are applied in various fields of research. They exhibit many advantages, and one of the most important is their possibility to be closely packed and to form a hexagonal grid that fully covers the Region o...

A Distributed Approach based on Transition Graph for Resolving Multimodal Urban Transportation Problem

All over the world, many research studies focus on developing and enhancing real-time communications between various transport stakeholders in urban environments. Such motivation can be justified by the growing importanc...

Power-Controlled Data Transmission in Wireless Ad-Hoc Networks: Challenges and Solutions

Energy scarcity and interference are two important factors determining the performance of wireless ad-hoc networks that should be considered in depth. A promising method of achieving energy conservation is the transmissi...

Combating the Looping Behavior: A Result of Routing Layer Attack

Routing layer is one of the most important layers of the network stack. In wireless ad hoc networks, it becomes more significant because nodes act as relay nodes or routers in the network. This characteristic puts them a...

Download PDF file
  • EP ID EP100049
  • DOI 10.14569/IJACSA.2014.051022#sthash.yjFX63PH.dpuf
  • Views 72
  • Downloads 0

How To Cite

Hitoshi Kono, Akiya Kamimura, Kohji Tomita, Yuta Murata, Tsuyoshi Suzuki (2014). Transfer Learning Method Using Ontology for Heterogeneous Multi-agent Reinforcement Learning. International Journal of Advanced Computer Science & Applications, 5(10), 156-164. https://europub.co.uk/articles/-A-100049