Explanation in second generation expert systems
Second generation expert systems
Mathematics and Computers in Simulation - Special issue: 3rd IMACS international workshop on qualitative reasoning and decision support systems
Causal Maps: Theory, Implementation, and Practical Applications in Multiagent Environments
IEEE Transactions on Knowledge and Data Engineering
Designing Comprehensible Agents
IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
An Agent Based Approach to Expert System Explanation
Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference
| Hi-index | 0.00 |
Multi-Agent Systems MAS are developed in various domains such as computer networks, simulation, etc. Despite their rapid growth, we have no control on their execution, and no one knows what effectively happens inside. Because of this ignorance, agent behaviours are not always clearly reproducible for humans. Our objective is to provide more transparency to users when it is required, to make them able to understand the way to manage the non-deterministic process, and to give them the possibility to become familiar with such dynamic and complex systems. Users need to know how the resolution has been going on, how and when interactions have been performed. Agent reasoning explanation gives an answer to these questions. It gives information about reasoning and events executed 'inside' one agent or among all agents. In this paper, we present a reasoning explanation approach for MAS based on an extended causal map.