کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
381229 | 1437471 | 2011 | 10 صفحه PDF | دانلود رایگان |

There is a chronic lack of shared application domains to test advanced research models and agent negotiation architectures in Multiagent Systems. In this paper we introduce a friendly testbed for that purpose. The testbed is based on The Diplomacy Game where negotiation and the relationships between players play an essential role. The testbed profits from the existence of a large community of human players that know the game and can easily provide data for experiments. We explain the infrastructure in the paper and make it freely available to the AI community.
► We provide a testbed, called DipGame, for experimenting on negotiations with humans.
► The Diplomacy Game domain has no random moves and negotiation is crucial in it.
► The negotiation language can be set between a provided language level hierarchy.
► The language is general. The specific domain vocabulary is separated from the syntax.
► The testbed includes an agent development framework and a human recruitment website.
Journal: Engineering Applications of Artificial Intelligence - Volume 24, Issue 7, October 2011, Pages 1137–1146