Abstract
Modelling other agents is a challenging topic in artificial intelligence research particularly when a subject agent needs to optimise its own decisions by predicting their behaviours under uncertainty. Existing research often leads to a monotonic set of behaviours for other agents so that a subject agent can not cope with unexpected decisions from the other agents. It requires creative ideas about developing diversity of behaviours so as to improve the subject agent’s decision quality. In this paper, we resort to evolutionary computation approaches to generate a new set of behaviours for other agents and solve the complicated agents’ behaviour search and evaluation issues. The new approach starts with the initial behaviours that are ascribed to the other agents and expands the behaviours by using a number of genetic operators in the behaviour evolution. This is the first time that evolutionary techniques are used to modelling other agents in a general multiagent decision framework. We examine the new methods in two well-studied problem domains and provide experimental results in support.
Highlights
Modelling other agents is an important issue in artificial intelligence (AI) research while intelligent agent technologies are applied in a wide range of applications
We choose the interactive dynamic influence diagrams (I-dynamic influence diagram (DID)) model as the representation of multiagent decision making and show how modelling other agents and its challenges are embedded in I-DID
We implement the new framework in Algorithm 3 and solve I-DIDs through using the genetic algorithm in the generation of new behaviours for other agents
Summary
Modelling other agents is an important issue in artificial intelligence (AI) research while intelligent agent technologies are applied in a wide range of applications. A good set of possible behaviours that prescribe how other agents act can allow a subject agent to optimise its decisions in their interactions. To effectively evaluate the quality of Memetic Computing the generated behaviour through evolutionary mechanism, we select a general multiagent interaction model, namely interactive dynamic influence diagrams (I-DIDs) [23], as the evaluation framework in which a subject agent optimises its decisions through modelling other agents’ behaviours. From a subject agent’s viewpoint, an I-DID model can represent possible behaviours of other agents and optimise its own decisions over time. Since it does not hold any assumption about other agents, it is an ideal sequential decision making framework for either collaborative or competitive agents.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
