Unified theories of cognition
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Communications of the ACM
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Reinforcement Learning: Past, Present and Future
SEAL'98 Selected papers from the Second Asia-Pacific Conference on Simulated Evolution and Learning on Simulated Evolution and Learning
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Dynamic agent composition from semantic web services
SWDB'04 Proceedings of the Second international conference on Semantic Web and Databases
Hi-index | 0.00 |
We present a novel cognitive agent architecture and demonstrate its effectiveness in the Sense and Respond Logistics (SRL) domain. SRL transforms the static, hierarchical architectures of traditional military models into re-configurable networks designed to encourage coordination among small peer units. Multi-agent systems are ideal for SRL because they can provide valuable automation and decision support from low-level control to high-level information synchronization. In particular, agents can be aware of and adapt to changes in the environment that may affect control and decision making. Our architecture, the Engine for Composable Logical Agents with Intuitive Reorganization (ECLAIR) is a framework for enabling rapid development of coherent agent systems that adapt to their environment once deployed. ECLAIR is based on cognitive theories for motivation and adaptation, including Piaget's Assimilation and Accommodation [21] and Damasio's Somatic Marker Hypothesis [6]. To demonstrate our preliminary work, we implemented a simple simulation environment where our agents handle the ordering and delivery of supplies among operational and supply units in several scenarios requiring adaptation of default behavior.