Title :
A characterization of sapient agents
Author :
Van Otterlo, Martijn ; Wiering, Marco ; Dastani, Mehdi ; Meyer, John-Jules
Author_Institution :
Dept. of Comput. Sci., Twente Univ., Enschede, Netherlands
fDate :
30 Sept.-4 Oct. 2003
Abstract :
We present a proposal to characterize sapient agents in terms of cognitive concepts and abilities. In particular, a sapient agent is considered as a cognitive agent that learns its cognitive state and capabilities through experience. This characterization is based on formal concepts such as beliefs, goals, plans and reasoning rules, and formal techniques such as relational RL. We identify several aspects of cognitive agents that can be evolved through learning and indicate how these aspects can be learned. Other important features such as the social environment, interaction with other agents or humans and the ability to deal with emotions, will also be discussed. Finally, the directions for further research on sapient agents are described.
Keywords :
cognition; decision making; learning (artificial intelligence); multi-agent systems; agent interaction; cognitive agent; reasoning rules; relational reinforcement learning; sapient agent characterization; social environment; Bayesian methods; Computer science; Decision making; Fuzzy logic; Humans; Intelligent agent; Intelligent systems; Learning; Neural networks; Proposals;
Conference_Titel :
Integration of Knowledge Intensive Multi-Agent Systems, 2003. International Conference on
Print_ISBN :
0-7803-7958-6
DOI :
10.1109/KIMAS.2003.1245041