Home // ICAS 2019, The Fifteenth International Conference on Autonomic and Autonomous Systems // View article

Transfer Learning Approach for Autonomous Agents in Collective Games

Authors:
Vanya Markova
Ventseslav Shopov

Keywords: autonomous agents; reinforcement learning; transfer learning

Abstract:
The aim of this study is to present a new approach for Transfer Learning in collective games. This framework is a set of methods for transferring accumulated knowledge. In this way, autonomous agents share their knowledge in order to achieve better performance. The main hypothesis in the study is that the group of agents who exchange knowledge performs better than the same group without Transfer Knowledge, under the same conditions.

Pages: 51 to 54

Copyright: Copyright (c) IARIA, 2019

Publication date: June 2, 2019

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-712-2

Location: Athens, Greece

Dates: from June 2, 2019 to June 6, 2019