Effects of Communication in Cooperative Q-Learning
Darbyshire, Paul and Wang, D (2010) Effects of Communication in Cooperative Q-Learning. International Journal of Innovative Computing, Information and Control, 6 (5). pp. 2113-2126. ISSN 1349-4198
Abstract
Reinforcement learning has been utilized to investigate the distributed learn- ing problem in many different multi-agent and team-based scenarios. Invariably, using a distributed learning approach by allowing agents to exchange what they have learned, by either direct communication or by episodic exchanges, the team does better in terms of achieving its goals. The cause-effect relationship between communication and improved performance has been studied in a number of different team based scenarios; however, it is difficult to find a detailed analysis of the effect the communication has as a function of time on the elements of the simulation. Of particular interest is the effect on the learning of agents when part of a communicating multi-agent system. Studies show the effects of cooperative learning in the form of accelerated group learning rates; but it is difficult to pinpoint through the literature exactly how this observed effect is realized within individ- ual agents over time. This paper investigates the effect of communication as a function of time on a multi-agent simulation based on a military distillation, utilizing a modified Q-learning algorithm.
Item type | Article |
URI | https://vuir.vu.edu.au/id/eprint/7339 |
Subjects | Historical > Faculty/School/Research Centre/Department > School of Management and Information Systems Historical > FOR Classification > 0801 Artificial Intelligence and Image Processing Historical > SEO Classification > 970108 Expanding Knowledge in the Information and Computing Sciences |
Keywords | ResPubID21439, ResPubID20955. agent communication, reinforcement learning, multi-agent systems, complex system, learning rates, knowledge landscape |
Citations in Scopus | 4 - View on Scopus |
Download/View statistics | View download statistics for this item |