Journal ArticleDOI
Designing and building a negotiating automated agent
Sarit Kraus,Daniel Lehmann +1 more
- Vol. 11, Iss: 1, pp 132-171
TLDR
A general structure for a Negotiating Automated Agent that consists of five modules: a Prime Minister, a Ministry of Defense, a Foreign Office, a Headquarters and Intelligence, and a Diplomacy player, which was evaluated and consistently played better than human players.Abstract:
Negotiations are very important in a multiagenl environment, particularly, in an environment where there are conflicts between the agents, and cooperation would be beneficial. We have developed a general structure for a Negotiating Automated Agent that consists of five modules: a Prime Minister, a Ministry of Defense, a Foreign Office, a Headquarters and Intelligence. These modules are implemented using a dynamic set of local agents belonging to the different modules. We used this structure to develop a Diplomacy player. Diplomat. Playing Diplomacy involves a certain amount of technical skills as in other board games, but the capacity to negotiate, explain, convince, promise, keep promises or break them, is an essential ingredient in good play. Diplomat was evaluated and consistently played better than human players.read more
Citations
More filters
Journal ArticleDOI
Automated Negotiation: Prospects, Methods and Challenges
Journal ArticleDOI
Collaborative plans for complex group action
Barbara J. Grosz,Sarit Kraus +1 more
TL;DR: A revised and expanded version of SharedPlans that reformulates Pollack's (1990) definition of individual plans to handle cases in which a single agent has only partial knowledge and has the features required by Bratman's (1992) account of shared cooperative activity.
Journal ArticleDOI
Reaching agreements through argumentation: a logical model and implementation
TL;DR: A logical model of the mental states of the agents based on a representation of their beliefs, desires, intentions, and goals is presented and a general Automated Negotiation Agent is implemented, based on the logical model.
Journal ArticleDOI
Using similarity criteria to make issue trade-offs in automated negotiations
TL;DR: In this article, the authors present a trade-off strategy where multiple negotiation decision variables are traded-off against one another (e.g., paying a higher price in order to obtain an earlier delivery date or waiting longer to obtain a higher quality service).
References
More filters
Journal ArticleDOI
Negotiation as a Metaphor for Distributed Problem Solving
Randall Davis,Reid G. Smith +1 more
TL;DR: A framework called the contract net is presented that specifies communication and control in a distributed problem solver, and comparisons with planner, conniver, hearsay-ii, and pup 6 are used to demonstrate that negotiation is a natural extension to the transfer of control mechanisms used in earlier problem-solving systems.
Journal ArticleDOI
A blackboard architecture for control
TL;DR: The paper shows how opm, a blackboard control system for multiple-task planning, exploits these capabilities and shows how the architecture would replicate the control behavior of hearsay-ii and hasp.
Proceedings Article
Reactive reasoning and planning
TL;DR: The reasoning system that controls the robot is designed to exhibit the kind of behavior expected of a rational agent, and is endowed with the psychological attitudes of belief, desire, and intention, resulting in complex goal-directed and reflective behaviors.
Journal ArticleDOI
Social conceptions of knowledge and action: DAI foundations and open systems semantics
TL;DR: In this article, the authors discuss foundations for distributed artificial intelligence (DAI), with a particular critical analysis of Hewitt's Open Information Systems Semantics (OISS), and present a brief overview of current DAI research including motivations and concepts, and discusses some of the basic problems in DAI.