Resolving crises through automated bilateral negotiations
Abstract: We describe the development of an automated agent that can negotiate efficiently with people in crises. The environment is characterized by two negotiators, time constraints, deadlines, full information, and the possibility of opting out. The agent can play either role, with communications via a pre-defined language. The model used in constructing the agent is based on a formal analysis of the crises using game-theoretic methods and heuristics for bargaining. The agent receives messages sent by its opponent, analyzes them and responds. It also initiates discussion on one or more parameters of an agreement. Experimental results of simulations of a fishing dispute between Canada and Spain indicate that the agent played at least as well as, and in the case of Spain, significantly better than a human player. [Copyright &y& Elsevier]/nCopyright of Artificial Intelligence is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
t-test, comparing results of agent-human with results of human-human p13
Two sets of simulations were conducted One set of simulations was performed with Computer Science students at Bar Ilan University in Israel. This set was performed in order to compare the agent’s performance to the performance of people. The second set of simulations was conducted with Government and Politics students at the University of Maryland. While the Maryland simulations were designed to test hypotheses relating to foreign policy decision-making, they will be presented here as a reliability check of the main Bar Ilan results. Each student was told his/her role in the simulation and they had fifteen minutes to work out a strategy and check their options by means of the GDSS. Pg 13
Utility pointsAgreement reached – opting outComparing results of agent with result of humans
A simulation tool is developed that is able to support the negotiation of both people and automated agents. Pg 8.A realistic about a conflict between Canada and spain ( a fishing dispute) was used to evaluate the tool. pg 11
Goal:Our goal is the development of automated agents that can negotiate efficiently with people in crises.
The results of the experiments revealed that the agent played at least as well as, and in the case of one of the two roles, significantly better than a human player. Pg 16
SimulationSuch agents may be used, for example, inelectronic commerce and for training negotiators [15,18,32]. We focus on bilateral negotiations in simulated crises characterized by time constraints, deadlines, full information, and the possibility of opting out. Pg 1Hypothesis:Our hypothesis was that the agent would do at least as well as the human players in the negotiations. Pg 13
 |
Portfolio of Solutions web site has been initially developed in the scope of DRIVER+ project. Today, the service is managed by AIT Austrian Institute of Technology GmbH., for the benefit of the European Crisis Management. PoS is endorsed and supported by the Disaster Competence Network Austria (DCNA) as well as by the STAMINA and TeamAware H2020 projects. |