Learning of Communication for Negotiation and Emergence of Individuality by Reinforcement Learning using Neural Network

Summary

We think that communication in multi-agent system has two major meanings. One of them is to transmit one agent's observed information to the other. The other meaning is to transmit what an agent is thinking. Here we focus the latter and aim to the emergence of the autonomous and decentralized arbitration through communication among some agents. The communication contents and protocols are not prescribed and are acquired by learning using a reinforcement signal which is given to the agent after its action. The reinforcement signal is not shared with the other agents. In order to realize this learning, the agent often has to make a decision not only from the present communication signals but also from the past signals. Accordingly the system architecture using recurrent type (Elman) neural network is proposed. The ability of this architecture was examined by two and four agents negotiation problems. A variety of negotiation strategies emerged among the agents through the learning to avoid some conflict after their decisions.

Reference
3. Katsunari Shibata and Koji Ito:
Learning of Communication for Negotiation to Avoid Some Conflicts of Interests - Learning of Dynamic Communication Using Recurrent Neural Network -,
Trans. of SICE(The Society of Instrument and Control Engineers), Vol.35, No.11, pp.1346-1354, 1999.11 (in Japanese)
柴田克成, 伊藤宏司:
利害の衝突回避のための交渉コミュニケーションの学習と個性の発現 -リカレントニューラルネットを用いたダイナミックコミュニケーションの学習-,
計測自動制御学会論文誌, Vol.35, No.11, pp.1346-1354, 1999.11
[dynamic communication, recurrent neural network, negotiation, individuality]
pdf File (10 pages, 214kB)

2. K. Shibata and K. Ito :(ps file 8pages 288KB)
Emergence of Communication for Negotiation By a Recurrent Neural Network,
Proc. of ISADS (International Symposium on Autonomous Decentralized System) '99, pp.294-301, 1999.3

1. 柴田克成，伊藤宏司：(ps file 6pages 218KB (in japanese))
利害の衝突回避のための交渉コミュニケーションの学習と個性の発現,
第11回自律分散システムシンポジウム資料, pp.303-308, 1999.1
(in Japanese)