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

D-MFCLMin: A New Algorithm for Extracting Frequent Conceptual Links from Social Networks

Massive amounts of data in social networks have made researchers look for ways to display a summary of the information provided and extract knowledge from them. One of the new approaches to describe knowledge of the soci...

Image Compression of MRI Image using Planar Coding

In this paper a hierarchical coding technique for variable bit rate service is developed using embedded zero block coding approach. The suggested approach enhances the variable rate coding by zero tree based block-coding...

An Electrical Model to U-Slot Patch Antenna with Circular Polarization

The microstrip antenna is one of the best antenna structures, due to its low cost and compact design. In this paper, a coaxial feed circularly polarized square patch antenna is designed using the U-slot. The proposed ant...

Energy Efficient Cluster-Based Intrusion Detection System for Wireless Sensor Networks

Wireless sensor networks (WSNs) are network type where sensors are used to collect physical measurements. It has many application areas such as healthcare, weather monitoring and even military applications. Security in t...

A GRASP-based Solution Construction Approach for the Multi-Vehicle Profitable Pickup and Delivery Problem

With the advancement of e-commerce and Internet shopping, the high competition between carriers has made many companies rethink their service mechanisms to customers, in order to ensure that they stay competitive in the...

Download PDF file
  • EP ID EP100049
  • DOI 10.14569/IJACSA.2014.051022#sthash.yjFX63PH.dpuf
  • Views 111
  • 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