Strategy acquisition of agents in multi-issue negotiation

Shohei Yoshikawa, Takahiko Kamiryo, Yoshiaki Yasumura, Kuniaki Uehara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents a method for acquiring a strategy of an agent in multi-issue negotiation. This method learns how to make a concession to an opponent for realizing win-win negotiation. To learn the concession strategy, we adopt reinforcement learning. First, an agent receives a proposal from an opponent. The agent recognizes a negotiation state using the difference between their proposals and difference between their concessions. According to the state, the agent makes a proposal by reinforcement learning. A reward of the learning is a profit of an agreement and punishment of negotiation breakdown. The experimental results showed that agents could acquire a negotiation strategy that avoids negotiation breakdown and increases profits of an agreement. As a result, agents can acquire the action policy that strikes a balance between cooperation and competition.

Original languageEnglish
Title of host publicationProceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06
Pages933-939
Number of pages7
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2006 IEEE/WIC/ACM International Conference on Web Intelligence, WI'06 - Hong Kong
Duration: 2006 Dec 182006 Dec 22

Other

Other2006 IEEE/WIC/ACM International Conference on Web Intelligence, WI'06
CityHong Kong
Period06/12/1806/12/22

Fingerprint

Reinforcement learning
Profitability

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Yoshikawa, S., Kamiryo, T., Yasumura, Y., & Uehara, K. (2007). Strategy acquisition of agents in multi-issue negotiation. In Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06 (pp. 933-939). [4061498] https://doi.org/10.1109/WI.2006.160

Strategy acquisition of agents in multi-issue negotiation. / Yoshikawa, Shohei; Kamiryo, Takahiko; Yasumura, Yoshiaki; Uehara, Kuniaki.

Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06. 2007. p. 933-939 4061498.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yoshikawa, S, Kamiryo, T, Yasumura, Y & Uehara, K 2007, Strategy acquisition of agents in multi-issue negotiation. in Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06., 4061498, pp. 933-939, 2006 IEEE/WIC/ACM International Conference on Web Intelligence, WI'06, Hong Kong, 06/12/18. https://doi.org/10.1109/WI.2006.160
Yoshikawa S, Kamiryo T, Yasumura Y, Uehara K. Strategy acquisition of agents in multi-issue negotiation. In Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06. 2007. p. 933-939. 4061498 https://doi.org/10.1109/WI.2006.160
Yoshikawa, Shohei ; Kamiryo, Takahiko ; Yasumura, Yoshiaki ; Uehara, Kuniaki. / Strategy acquisition of agents in multi-issue negotiation. Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06. 2007. pp. 933-939
@inproceedings{798b2b7c0e8f40f08c8b8393df9d5e49,
title = "Strategy acquisition of agents in multi-issue negotiation",
abstract = "This paper presents a method for acquiring a strategy of an agent in multi-issue negotiation. This method learns how to make a concession to an opponent for realizing win-win negotiation. To learn the concession strategy, we adopt reinforcement learning. First, an agent receives a proposal from an opponent. The agent recognizes a negotiation state using the difference between their proposals and difference between their concessions. According to the state, the agent makes a proposal by reinforcement learning. A reward of the learning is a profit of an agreement and punishment of negotiation breakdown. The experimental results showed that agents could acquire a negotiation strategy that avoids negotiation breakdown and increases profits of an agreement. As a result, agents can acquire the action policy that strikes a balance between cooperation and competition.",
author = "Shohei Yoshikawa and Takahiko Kamiryo and Yoshiaki Yasumura and Kuniaki Uehara",
year = "2007",
doi = "10.1109/WI.2006.160",
language = "English",
isbn = "0769527477",
pages = "933--939",
booktitle = "Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06",

}

TY - GEN

T1 - Strategy acquisition of agents in multi-issue negotiation

AU - Yoshikawa, Shohei

AU - Kamiryo, Takahiko

AU - Yasumura, Yoshiaki

AU - Uehara, Kuniaki

PY - 2007

Y1 - 2007

N2 - This paper presents a method for acquiring a strategy of an agent in multi-issue negotiation. This method learns how to make a concession to an opponent for realizing win-win negotiation. To learn the concession strategy, we adopt reinforcement learning. First, an agent receives a proposal from an opponent. The agent recognizes a negotiation state using the difference between their proposals and difference between their concessions. According to the state, the agent makes a proposal by reinforcement learning. A reward of the learning is a profit of an agreement and punishment of negotiation breakdown. The experimental results showed that agents could acquire a negotiation strategy that avoids negotiation breakdown and increases profits of an agreement. As a result, agents can acquire the action policy that strikes a balance between cooperation and competition.

AB - This paper presents a method for acquiring a strategy of an agent in multi-issue negotiation. This method learns how to make a concession to an opponent for realizing win-win negotiation. To learn the concession strategy, we adopt reinforcement learning. First, an agent receives a proposal from an opponent. The agent recognizes a negotiation state using the difference between their proposals and difference between their concessions. According to the state, the agent makes a proposal by reinforcement learning. A reward of the learning is a profit of an agreement and punishment of negotiation breakdown. The experimental results showed that agents could acquire a negotiation strategy that avoids negotiation breakdown and increases profits of an agreement. As a result, agents can acquire the action policy that strikes a balance between cooperation and competition.

UR - http://www.scopus.com/inward/record.url?scp=42549143943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42549143943&partnerID=8YFLogxK

U2 - 10.1109/WI.2006.160

DO - 10.1109/WI.2006.160

M3 - Conference contribution

SN - 0769527477

SN - 9780769527475

SP - 933

EP - 939

BT - Proceedings - 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings), WI'06

ER -