Computational Intelligence, Volume 34, Number 1, 2018
COMPROMISING ADJUSTMENT STRATEGY BASED ON
TKI CONFLICT MODE FOR MULTI-TIMES BILATERAL
Tokyo University of Agriculture and Technology, Koganei, Tokyo, Japan
Bilateral multi-issue closed negotiation is an important class for real-life negotiations. Usually, negotiation
problems have constraints such as a complex and unknown opponent’s utility in real time, or time discounting. In
the class of negotiation with some constraints, the effective automated negotiation agents can adjust their behavior
depending on the characteristics of their opponents and negotiation scenarios. Recently, the attention of this study
has focused on the interleaving learning with negotiation strategies from the past negotiation sessions. By analyzing
the past negotiation sessions, agents can estimate the opponent’s utility function based on exchanging bids.
In this article, we propose a negotiation strategy that estimates the opponent’s strategies based on the past
negotiation sessions. Our agent tries to compromise to the estimated maximum utility of the opponent by the end
of the negotiation. In addition, our agent can adjust the speed of compromise by judging the opponent’s Thomas–
Kilmann conﬂict mode and search for the Pareto frontier using past negotiation sessions. In the experiments, we
demonstrate that the proposed agent has better outcomes and greater search technique for the Pareto frontier than
existing agents in the linear and nonlinear utility functions.
Received 15 November 2015; Revised 4 June 2016; Accepted 6 September 2016
Key words: automated negotiation, TKI conﬂict model, multiagent systems, agreement technology.
Negotiation is an important process in forming alliances and reaching trade agree-
ments. Research in the ﬁeld of negotiation is applied to various ﬁelds including economics,
social science, game theory, and artiﬁcial intelligence (e.g.,Kraus 2001; Faratin et al. 2002).
Agents can be used side-by-side with a human negotiator embarking on an important nego-
tiation task. They can alleviate some of the effort required of people during negotiations and
also assist people that are less qualiﬁed in the negotiation process. There may even be situa-
tions in which automated negotiators can replace the human negotiators. Another possibility
is for people to use these agents as a training tool, prior to actually performing the task.
Thus, success in developing an agent with negotiation capabilities has great advantages and
Recently, for automated negotiation agents in bilateral multi-issue closed negotiation,
the attention has focused on interleaving learning with negotiation strategies from past nego-
tiation sessions. By analyzing the past negotiation sessions, agents can adapt to domains
over time and use them to improve their strategies for future negotiations. However, some
outstanding issues regarding them remain, such as effective use of past negotiation sessions.
In particular, the way of understanding the opponent’s strategy and negotiation scenarios
from the past sessions is unclear. In other words, it is still an open and interesting problem to
design more efﬁcient automated negotiation strategies against a variety of negotiating oppo-
nents in different negotiation domains by utilizing the past negotiation sessions. Another
key point in achieving automated negotiation in real life is the nonlinearity of the util-
ity functions. Many real-world negotiation problems assume the multiple nonlinear utility
Address correspondence to Katsuhide Fujita, Tokyo University of Agriculture and Technology, Koganei, Tokyo, Japan;
© 2017 Wiley Periodicals, Inc.