MACC'97 Poster session
To realize real world learning we use multi agent system (called Agent network) which has reusability and genelalizability. Main point for introduce learning ability is (1)Maintaining real world pattern information directly. (2)Strong formalization to reduce learning space. We already applied agent network model for manipulator. In this paper we introduce contract mechanism to the agent network model, and show that distributed knowledge is integrated to accomplish simple chasing task.
Agent network, Contract net, Autonomous Learning, Symbol Grounding, Distributed AI, Neural networks, Real world computing.
paper