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

 Algorithm design for a supply chain equilibrium management model

 In this paper, we consider a complementary model for the equilibrium management of supply chain. In order to give an optimal decision for the equilibrium management, we propose a new algorithm based on an estimate...

Generating an Educational Domain Checklist through an Adaptive Framework for Evaluating Educational Systems

The growth of the Internet and related technologies has enabled the development of a new breed of dynamic websites that is growing rapidly in use and that has had a huge impact on many businesses. One type of websites th...

Benefits Management of Cloud Computing Investments

This paper examines investments in cloud computing using the Benefits Management approach. The major contribution of the paper is to provide a unique insight into how organizations derive value from cloud computing inves...

Context-Aware Mobile Application Task Offloading to the Cloud

One of the benefits of mobile cloud computing is the ability to offload mobile applications to the cloud for many reasons including performance enhancement and reduced resource consumption. This paper is concerned with o...

Solution of Electromagnetic and Velocity Fields for an Electrohydrodynamic Fluid Dynamical System

We studied the temporal evolution of the electromagnetic and velocity fields in an incompressible conducting fluid by means of computer simulations from the Navier Stokes and Maxwell’s equations. We then derived the se...

Download PDF file
  • EP ID EP100049
  • DOI 10.14569/IJACSA.2014.051022#sthash.yjFX63PH.dpuf
  • Views 118
  • 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