Abstract
This paper presents a method for acquiring a concession 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 the 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 a punishment of negotiation breakdown. The experimental results showed that the agents could acquire the 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 language | English |
|---|---|
| Pages (from-to) | 161-171 |
| Number of pages | 11 |
| Journal | Web Intelligence and Agent Systems |
| Volume | 7 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2009 |
| Externally published | Yes |
Fingerprint
Keywords
- Concession strategy
- Multi-issue negotiation
- Reinforcement learning
- Win-win negotiation
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Computer Networks and Communications
Cite this
Acquisition of a concession strategy in multi-issue negotiation. / Yasumura, Yoshiaki; Kamiryo, Takahiko; Yoshikawa, Shohei; Uehara, Kuniaki.
In: Web Intelligence and Agent Systems, Vol. 7, No. 2, 2009, p. 161-171.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Acquisition of a concession strategy in multi-issue negotiation
AU - Yasumura, Yoshiaki
AU - Kamiryo, Takahiko
AU - Yoshikawa, Shohei
AU - Uehara, Kuniaki
PY - 2009
Y1 - 2009
N2 - This paper presents a method for acquiring a concession 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 the 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 a punishment of negotiation breakdown. The experimental results showed that the agents could acquire the 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 concession 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 the 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 a punishment of negotiation breakdown. The experimental results showed that the agents could acquire the 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.
KW - Concession strategy
KW - Multi-issue negotiation
KW - Reinforcement learning
KW - Win-win negotiation
UR - http://www.scopus.com/inward/record.url?scp=68249161927&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=68249161927&partnerID=8YFLogxK
U2 - 10.3233/WIA-2009-0160
DO - 10.3233/WIA-2009-0160
M3 - Article
AN - SCOPUS:68249161927
VL - 7
SP - 161
EP - 171
JO - Web Intelligence
JF - Web Intelligence
SN - 2405-6456
IS - 2
ER -