Training a Cognitive Agent to Acquire and Represent Knowledge from RSS feeds onto Conceptual Graphs

Imitative processes such as knowledge transference, have been long pursued goals of Artificial Intelligence. The significance of knowledge acquisition in animals and humans has been studied by scientists from the beginning of the 20th century. Our research focuses on acquiring information via observational imitation and agent-user interaction. The cognitive agent described here emulates a perceptive and learning system, trained for the purpose of self-augmenting its learning capabilities, in order to achieve knowledge acquisition. The agent’s purpose is to learn the semiotics of Rich Site Summary feeds through empirical observation. It is also trained to autonomously represent that knowledge in a manner that is both logically sound, and computationally tractable, through the use of conceptual graphs. The main novel algorithm enabling this agent is based upon Reinforcement Learning, by approximating decisions through distributional and relational semantics. Keywords–Cognitive Agent; Reinforcement Learning; Conceptual Graphs; Expert Systems;